jurnal riset informatika vol. 1, no. 2 maret 2019 p-issn: 2656-1743 e-issn: 2656-1735 65 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. sistem deteksi plat kendaraan dengan menggunakan metode k-nearest neghbour (knn) farida 1, zahir zainuddin 2 , supriadi sahibu 3 1 sistem informasi stmik bina adinata faridahvaryd4@gmail.com 2 teknik informatika universitas hasanuddin zainuddinzahir@gmail.com 3 pascasarjana sistem komputer stmik handayani makassar http://pps.handayani.ac.id/ supriadi.dit@gmail.com abstrak sistem pemantauan dan manajemen kendaraan berbasis plat nomor kendaraan telah berkembang, identifikasi dan pengenalan plat nomor menjadi aplikasi utama dalam bidang lalu lintas. terlalu banyak kejadian dalam berlalu lintas, salah satunya, seperti melewati batas stop di jalan sehingga mengganggu para pengendara lainnya, hal ini paling banyak terjadi dan bahkan sering terjadi di kota-kota bahkan daerah sekalipun. tujuan dari penelitian ini adalah untuk mengekstraksi dan mengenali plat nomor dari citra kendaraan yang melakukan pelanggaran sehingga dapat digunakan sebagai data set dalam membuat laporan penentuan sanksi yang sesuai dengan jenis pelanggaran kendaraan tersebut. penelitian ini menggunakan proses ekstraksi pengolahan citra gambar sehingga metode yang sesuai dengan penelitian ini adalah k-nearest neighbour, dengan menggunakan metode tersebut akan memudahkan dalam proses pendeteksiannya. karena metode ini tidak menggunakan perulangan. prose ini dimulai dengan menyiapkan dari citra latih tahap kemudian melakukan tahapan pengenalan citra. pengenalan citra merupakan proses mencocokan data citra digital yang sudah dirubah menjadi sebuah matriks kemudian dicocokan dengan dataset yang ada sehingga dapat diketahui hasilnya yang berupa laporan. kata kunci: open cv, k-nearest neighbour abstrack the monitoring system and managemen of vehicle have developed. identification and number plat recognition in the field of traffic one of them is like passing the stop line on the road so that is disturbs other drivers, this is the most and even often occurs in big city cities even regions. the purpose of this study is to extract and recognize license plates from the image of the vehicle, that infringes so that it can be used as a dataset in making reports on determining sanctions that are appropriate to the type of violation of the vehicle. this study uses an image processing extraction process so that method according to this method is knearest neighbour, using this method will facilitate the detection process because this method does not use looping, this process begins by preparing a training image and then performing the image recognition stage. image recognition is a process of matching digital image data that has been converted into a matrix and then matched with existing datasets so that the result can be known in the form of reports keywords: open cv, k-nearest neighbour, pendahuluan deteksi plat kendaraan yang merupakan sistem pemantauan dan manajemen kendaraan berbasis plat nomor kendaraan telah berkembang, identifikasi dan pengenalan plat nomor menjadi aplikasi utama dalam bidang lalu lintas. terlalu banyak kejadian dalam berlalu lintas, salah satunya, seperti melewati batas stop di jalan (fadila, 2017) sehingga pelanggaran lalu lintas (ruslianto & harjoko, 2013) ini http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 2 maret 2019 66 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. mengganggu para pengendara lainnya, hal ini paling banyak dan bahkan sering terjadi di kota-kota bahkan daerah sekalipun. olehnya itu didesign pengelolaan citra pendeteksi plat kendaraan. tujuannya adalah untuk mengekstraksi dan mengenali plat nomor dari citra kendaraan yang melakukan pelanggaran sehingga dapat digunakan sebagai data set dalam membuat laporan penentuan sanksi yang sesuai dengan jenis pelanggaran kendaraan tersebut. telah banyak penelitian mengenai sistem pengenalan plat nomor dengan pengolahan citra namun, dalam penelitian ini dikembangkan sistem pengenalan citra plat kendaraan setelah melewati batas stop dan hal ini mampu menjadi terobosan baru dalam ketertiban lalu lintas sehingga para pengendara mampu menjadi lebih tertib dan disiplin. penelitian ini menggunakan proses ekstraksi pengolahan citra gambar sehingga metode yang sesuai dengan penelitian ini adalah knearest neighbour (sari, 2011), (budianto, ariyuana, & maryono, 2018), dengan menggunakan metode tersebut akan memudahkan dalam proses pendeteksiannya. metode penelitian metode k-nearest neighbour (knn) merupakan salah satu metode untuk melakukan klasifikasi terhadap objek berdasarkan data pembelajaran yang jaraknya paling dekat dengan objek tersebut. tujuannya adalah untuk mengklasifikasikan objek baru berdasarkan atribut dan data training. klasifikasi dilakukan tanpa menggunakan model tetapi hanya berdasarkan memori. algoritma k-nearest neighbour menggunakan klasifikasi ketetanggaan sebagai prediksi terhadap data baru (fauziah, sulistyowati, & asra, 2019). pada fase training, algoritma ini hanya melakukan penyimpanan vektor-vektor fitur dan klasifikasi data training sampel a. rancangan sistem perancangan ini terdapat beberapa komponen yang saling berkaitan serta saling mendukung dan membentuk sebuah rangkaian. sistem ini rencananya akan dipasang di lampu merah lalu lintas dan juga mampu mendeteksi plat kendaraan, ketika kendaraan tersebut melakukan pelanggaran dalam artian melewati batas stop lampu merah lalu lintas maka sistem akan langsung mendeteksi plat kendaraan tersebut kemudian dimasukkan ke dalam daftar kendaraan yang melakukan pelanggaran lalu lintas. gambar 1. rancangan sistem jenis penelitian penelitian ini menggunakan pendekatan kuantitatif waktu dan tempat penelitian penelitian ini direncanakan akan dilakukan di wilayah bulukumba target/subjek penelitian target atau subject dari penelitian ini adalah plat kendaraan yang berwarna hitam baik kendaraan roda dua maupun roda empat. data, intrumen, dan teknik pengumpulan data 1. penelitian ke perpustakaan (library research), yaitu pengumpulan data dengan cara membaca buku melalui literature, tutorial-tutorial maupun artikel dari internet yang bersifat ilmiah yang ada hipatitisnya dengan materi pembahasan. 2. penelitian lapangan (field research), yaitu dilakukan dengan cara mengumpulkan data secara langsung kepada objek penelitian yaitu pada pembina atau guru yang bersangkutan dengan penelitian. teknik analisis data penelitian ke perpustakaan (library research), yaitu pengumpulan data dengan cara membaca buku melalui literature, tutorial-tutorial maupun artikel dari internet yang bersifat ilmiah yang ada hipatitisnya dengan materi pembahasan. penelitian lapangan (field research), yaitu dilakukan dengan cara mengumpulkan data secara langsung kepada objek penelitian yaitu pada pembina atau guru yang bersangkutan dengan penelitian. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 2 maret 2019 p-issn: 2656-1743 e-issn: 2656-1735 67 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. hasil penelitian dan pembahasan setelah citra telah disiapkan dari citra latih tahap selanjutnya perlu dilakukan tahapan pengenalan citra. pengenalan citra merupakan proses mencocokan data citra digital yang sudah dirubah menjadi sebuah matriks kemudian dicocokan dengan data set yang ada sehingga dapat diketahui menjadi laporan (output) berupa text. keberhasilan suatu pengujian dipengaruhi juga dengan jumlah data set yang dimiliki sehingga hasilnya sangat bergantung. data set memiliki banyak varian sangat bagus karena tinggak kegagalan akan menjadi berkurang. proses dimana dilakukan untuk menghitung tingkat akurasi dari hasil pengidentifikasian citra plat nomor kendaraan pada mobil pribadi (plat warna hitam) dengan menggunakan metode knearest neighbour seberapa besar terjadinya kesalahan atau berapa besar terjadinya kebenaran dalam proses identifikasian tersebut.adapun cara menghitung tingkat akurasi adalah sebagai berikut: 𝐴𝑘𝑢𝑟𝑎𝑠𝑖 = 𝐽𝑢𝑚𝑙𝑎ℎ 𝑝𝑟𝑒𝑑𝑖𝑘𝑠𝑖 𝑏𝑒𝑛𝑎𝑟 𝑗𝑢𝑚𝑙𝑎ℎ 𝑡𝑜𝑡𝑎𝑙 𝑝𝑟𝑒𝑑𝑖𝑘𝑠𝑖 𝑥 100% (1) jumlah prediksi benar adalah jumlah record data uji yang diprediksi kelasnya menggunakan metode klasifikasi dan hasilnya sama dengan kelas sebenarnya. sedangkan jumlah total prediksi adalah jumlah keseluruhan record yang diprediksi kelasnya (seluruh data uji). metode klasifikasi berusaha untuk mencari model yang memiliki tingkat akurasi yang tinggi ketika model tersebut diterapkan pada data uji. a. tahapan pra pengolahan pra pengolahan melibatkan dua proses yaitu merubah resolusi dan mengkonversi ruang warna. selain itu pengolahan juga melibatkan lokalisasi, lokalisasi ini berfungsi untuk memproses binarisasi dan mengubah citra kedalam bentuk black white, proses pengolahan inilah yang disebut sebagai thresholding atau tingkat kemiripan gambar. 1. merubah citra warna dalam proses ini citra yang berwarna akan di ubah ke citra grayscale ( keabu-abuan ) tujuannya adalah untuk mempermudah dalam pengidentifikasian citra plat nomor yang dibaca. gambar 2. citra plat asli gambar 2 tersebut merupakan gambar citra asli sebelum di ubah ke bentuk grayscale ( keabuabuan ) bentuk hitam putih dari hasil pengolahan tersebut dapat dilihat pada gambar di bawah ini. gambar 3. citra plat keabuan grayscaling adalah proses awal yang banyak dilakukan dalam image processing, hal ini dilakukan bertujuan untuk menyederhanakan model citra. pada awalnya citra rgb umumnya terdiri dari 3 layer matrik yaitu r-layer, g-layer dan b-layer. bila setiap proses perhitungan dilakukan menggunakan tiga layer, berarti dilakukan tiga perhitungan yang sama. sehingga konsep itu diubah dengan mengubah 3 layer di atas menjadi 1 layer matrik grayscale dan hasilnya adalah citra grayscale. citra ini tidak mempunyai elemen warna seperti citra sebelum diubah, melainkan mempunyai derajat keabuan. gambar 4. citra hasil konversi biner setelah proses grayscaling maka dilanjutkan ke proses pengkonversian citra binary, setelah itu yang dapat menghasilkan pencarian nilai threshold atau tingkat kemiripan. b. proses pengenalan k-nearest neighbour (knn) merupakan metode yang bersifat supervised dimana hasil dari query distance yang baru diklasifikasikan berdasarkan mayoritas kategori pada knn. pada vase training sample. pada fase ini fitur-fitur yang sama di hitung untuk testing data ( jneis klasifikasinya belum diketahui ). jarak dari vector yang baru ini terhadap seluruh vector training data sample dihitung. dan sejumlah k buah yang paling dekat diambil beberapa analogi metode knn : a. analogi metode klasifikasi knn ( k – nearest neihgbour ) dimana k = 1 http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 2 maret 2019 68 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. gambar 5. analogi knn dengan k=1 dari gambar 5 di atas jelas terlihat bahwa data uji huruf e memiliki euclidean 1 dengan huruf e yang berada di dalam dataset sehingga ketika melakukan pengujian data maka akan ditemukan hasil euclidean distance antara data uji dengan data set yaitu 1. gambar 6. analogi knn dengan k =2 dari gambar 6 di atas jelas terlihat bahwa data uji huruf e memiliki euclidean 2 dengan huruf e yang berada di dalam dataset sehingga ketika melakukan pengujian data maka akan ditemukan hasil euclidean distance antara data uji dengan data set yaitu 2. gambar 7. analogi knn dengan k=3 dari gambar 7 di atas jelas terlihat bahwa data uji huruf e memiliki euclidean 3 dengan huruf e yang berada di dalam dataset sehingga ketika melakukan pengujian data maka akan ditemukan hasil euclidean distance antara data uji dengan data set yaitu 3 dari proses ekstraksi menggunakan metode knn didapatkan hasil pengenalan sebagai berikut: gambar 8. deteksi plat dengan gambar langsung . gambar 9. deteksi plat secara langsung pengujian dilakukan pada plat kendaraan dengan kondisi baik dan plat kendaraan dengan kondisi baik dan plat kendaraan dengan kondisi yang kurang baik, dimana setiap plat diuji 4 kali berdasarkan jarak, sudut dan threshold yang diberikan. pengujian dilakukan menggunakan kamera webcam dengan raspberry pi spesifikasi prosesor mini. plat kendaraan yang baik adalah plat kendaraan yang karakter dan bentuk plat tidak rusak (sempurna) dan hanya terdapat sedikit noise ( kotoran ). sedangkan plat kendaraan yang kurang baik adalah plat kendaraan ang karakter dan bentuk plat tidak sempurna serta memiliki banyak noise atau kotoran pada plat. b. hasil pengujian plat kendaraan table 1. hasil pengujian jarak 40 cm no no. plat hasil pengenalan keterangan 1 b 457uty b457uty sukses 2 dn5269vk dn5269vk sukses 3 dd6656hk dd6656hk sukses 4 dn4505vt dn4505vt sukses 5 dd 5154 ku dd 5154 ku sukses 6 dn3742md dn3742m0 gagal 7 dd 3333 yh dd 3333 yh sukses 8 dd 1473 ya dd 1473 ya sukses 9 dn 4112 ye dn 4112 ye sukses 10 dd 5804 cj dd 5804 cj sukses 11 dn 4879 yc dn 4879 yc sukses http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 2 maret 2019 p-issn: 2656-1743 e-issn: 2656-1735 69 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. no no. plat hasil pengenalan keterangan 12 dd 4353 xy dd 4353 xy sukses 13 dn 6330 vm dn6330vm gagal 14 b 6703 wjf b 6703 wjf sukses 15 dd 9412 xu dd 9412 xu sukses 16 dd 5678 nt dd 5678 nt sukses 17 dd 6565 by dd6565by sukses 18 dd 1719 ni dd1719ni sukses dari hasil pengujian pada table 4.1 dapat diketahui bahwa persentase rata-rata keakuratan system pengenalan plat kendaraan dengan jarak 40 cm ∑(𝑗𝑢𝑚𝑙𝑎ℎ 𝑠𝑢𝑘𝑠𝑒𝑠) ∑(𝑗𝑢𝑚𝑙𝑎ℎ 𝑆𝑎𝑚𝑝𝑒𝑙) = 16 18 x 100% = 88,88% tabel 2 hasil pengujian dengan jarak 50 cm no no. plat hasil pengenalan keterangan 1 b 457uty b457uty sukses 2 dn5269vk dn5269vk sukses 3 dd6656hk dd6656hk sukses 4 dn4505vt dn450svt gagal 5 dd 5154 ku dd 5154 ku sukses 6 dn3742md dn3742m0 gagal 7 dd 3333 yh dd 3333 yh sukses 8 dd 1473 ya dd 1473 ya sukses 9 dn 4112 ye dm 4112 ye gagal 10 dd 5804 cj dd 5804 cj sukses 11 dn 4879 yc dn 4879 yc sukses 12 dd 4353 xy dd 4353 xy sukses 13 dn 6330 vm dn 6330 vm sukses 14 b 6703 wjf b 6703 wjf sukses 15 dd 9412 xu dd 9412 xu sukses 16 dd 5678 nt dd 5678 nt sukses 17 dd 6565 by dd6565by sukses 18 dd 1719 ni dd1719ni sukses dari table di atas di tentukan tingkat akurasinya dengan menggunakan langkah berikut. ∑(𝑗𝑢𝑚𝑙𝑎ℎ 𝑠𝑢𝑘𝑠𝑒𝑠) ∑(𝑗𝑢𝑚𝑙𝑎ℎ 𝑆𝑎𝑚𝑝𝑒𝑙) = 12 18 x 100% = 85,71 % table 3 hasil pengujian dengan jarak 60 cm no no. plat hasil pengenalan keterangan 1 b 457uty b457uty sukses 2 dn5269vk dn5269vk sukses 3 dd6656hk dd6656hk sukses 4 dn4505vt dn450svt gagal 5 dd 5154 ku d0 5154 ku gagal 6 dn3742md dn3742m0 gagal 7 dd 3333 yh dd 3333 yh sukses 8 dd 1473 ya d0 1473 ya gagal 9 dn 4112 ye dm 4112 ye gagal 10 dd 5804 cj dd 5b04 cj gagal 11 dn 4879 yc dn 4879 yc sukses 12 dd 4353 xy dd 4353 xy sukses 13 dn 6330 vm dn6330vn gagal 14 b 6703 wjf b 6703 wjf sukses 15 dd 9412 xu dd 9412 xu sukses 16 dd 5678 nt d0 5678 nt sukses 17 dd 6565 by dd6565by sukses 18 dd 1719 ni dd1719ni sukses dari table di atas dapat di tentukan tingkat akurasinya dengan menggunakan persamaan berikut : ∑(𝑗𝑢𝑚𝑙𝑎ℎ 𝑠𝑢𝑘𝑠𝑒𝑠) ∑(𝑗𝑢𝑚𝑙𝑎ℎ 𝑆𝑎𝑚𝑝𝑒𝑙) = 10 18 x 100% = 55,55% adapun faktor-faktor lain yang menyebabkan kegagalan proses pengenalan plat kendaraan adalah noise yang ada pada plat kendaraan. penggunaan threshold yang kecil belum mampu menghilangkan noise dengan baik sehingg menyebabkan proses karakter tidka tersegmentasi dengan baik. sedangkan penggunaan threshold yang tinggi juga mempengaruhi proses pengenalan karakter, walaupun noise dapat dihilangkan akan tetapi berpengaruh pada penitisan lebar dari karakter, sehingg akan menyebabkan prubahan bentuk karakter sperti pada karakter n dan h, s dan 5, b dan 8 dan d dan 0. simpulan dan saran simpulan dari hasil peneltian yang telah dilakukan pada citra plat nomor kendaraan pribadi (plat nomor warn hitam ) dengan menggunakan metode knearest neighbour dapat diperoleh kesimpulan sebagai berikut: citra dapat diidentifikasi jika cahaya yang ada pada citra tidak terllau besar maupun kecacatan tidak terllu parah karena akan menimbulkan kesalahan dalam identifikasi. dalam pengidentifikasian citra dibutuhkan banyak data set sehingga dalam pengidentifikasian tidak terjadi kesalahan karena dalam proses pengidentifikasian ini mencari kemiripam dengan data set yang mirip dengan data set yang sudah ada jika tidak ditemukan maka akan terbaca sebagai data set yang lain sehingga terjadi kesalahan. hal ini merupakan karakter dari metode k-nearest neighbor. dalam proses ini dperoleh tingkat akurasi sebesar 88 % dengan jarak 40 cm dan akurasi 85 % dengan jark 50 cm dan 55 % dengan jarak 60 cm. penggunaan metode k-nearest neighbor lebih tepat karena metode ini tidak tidak melakukan perulangan dalam proses pencocokan sehingga lebih efisien dalam melakukan pengujian. saran perlu adanya penetapan nilai threshold yang baik untuk menangani tingkat noise yang ada pada plat serta pencahayaan pada plat sehingga karakter pada plat kendaraan dapat tersegmentasi dengan http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 2 maret 2019 70 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. baik. sistem ini perlu dikembangkan lebih lanjut sehingga nantinya mampu memberikan hasil yang lebih baik dalam pengenalan karakter sehingga dapat diimplementasikan pada system transportasi daftar referensi budianto, a., ariyuana, r., & maryono, d. (2018). perbandingan k-nearest neighbor (knn) dan support vector machine (svm) dalam pengenalan karakter plat kendaraan bermotor. jiptek : jurnal ilmiah pendidikan teknik dan kejuruan, 11(1). https://doi.org/10.20961/jiptek.v11i1.18018 fadila, a. (2017). tingkat kesadaran berlalu lintas pengendara sepeda motor di surabaya selatan. kajian moral dan kewarganegaraan, 5(3), 1036– 1051. retrieved from https://jurnalmahasiswa.unesa.ac.id/index.php/ju rnal-pendidikankewarganegaraa/article/view/22055 fauziah, s., sulistyowati, d. n., & asra, t. (2019). optimasi algoritma vector space model dengan algoritma knearest neighbour pada pencarian judul artikel jurnal. jurnal pilar nusa mandiri, 15(1), 21–26. https://doi.org/10.33480/pilar.v15i1.27 ruslianto, i., & harjoko, a. (2013). pengenalan karakter plat nomor mobil secara real time. ijeis (indonesian journal of electronics and instrumentation systems), 1(2), 101–110. https://doi.org/10.22146/ijeis.1967 sari, m. i. (2011). desain segmentasi dan pengenalan karakter pada plat nomor kendaraan. in konferensi nasional ict-m politeknik telkom (pp. 250–253). politeknik telkom. retrieved from http://journals.telkomuniversity.ac.id/knip/articl e/view/556 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 3 juni 2019 p-issn: 2656-1743 e-issn: 2656-1735 113 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional implementasi metode simple additive weighting (saw) pada sistem pendukung keputusan untuk menyeleksi saham prima ratna kusumawardani1, achmad solichin2 1,2) prodi teknik informatika, fakultas teknologi informasi universitas budi luhur, jakarta 1)ratna.kusumawardani@budiluhur.ac.id, 2)achmad.solichin@budiluhur.ac.id abstrak pada penelitian ini dibahas mengenai sistem pendukung keputusan untuk menyeleksi saham prima. masalah yang terjadi dalam penelitian adalah adanya kalangan umum maupun profesional yang masih melakukan analisis fundamental secara manual dalam pengambilan keputusan pembelian saham. penggunaan sistem pendukung keputusan diharapkan dapat membantu dalam proses pengolahan data saham yang memiliki kategori prima menjadi lebih efektif. metode simple additive weighting (saw) ini dipilih karena mampu menyeleksi alternatif terbaik dari sejumlah alternatif. dalam hal ini alternatif yang dimaksudkan yaitu saham prima berdasarkan kriteria-kriteria yang ditentukan. penelitian dilakukan dengan menentukan nilai bobot untuk setiap atribut, kemudian dilakukan proses perankingan yang akan menentukan alternatif yang optimal, yaitu saham terbaik. hasil penelitian berupa aplikasi sistem pendukung keputusan penyeleksi saham prima yang dibangun dengan bahasa pemrograman java dan basisdata mysql. aplikasi ini berguna untuk memilih alternatif yang terbaik untuk mendapatkan saham prima. para investor yang akan berinvestasi di saham, tidak akan salah membeli saham karena sudah memiliki daftar nama-nama saham prima. kata kunci: saw, spk, seleksi saham, perankingan, pendukung keputusan abstract in this study we proposed the decision support system for selecting prime stock. problems that occur in the research is the general public as well as professionals who are still doing fundamental analysis in decision making stock purchases manually. the use of a decision support system is expected to assist in the data processing stocks that have become more effective prime category. simple additive weighting (saw) method have been selected because it is able to select the best alternative from a number of alternatives. in this case the alternative meant that prime stocks based on specified criteria. research carried out by determining the weight value for each attribute, then do ranking process that will determine the optimal alternative, which is the best stock. results of the research is a decision support system application prime stock selectors that is built using the java programming language and mysql database. this application allows you to choose the best alternative to get prime stock. the investors who will invest in stocks, will not go wrong b uying stocks because it already had a list of names of the prime stocks. keywords: saw, dss, stock selection, ranking, decision support pendahuluan investasi merupakan suatu langkah seseorang dalam pemenuhan kebutuhan di masa yang akan datang. dewasa ini, dunia investasi tidak lagi didominasi oleh jenis investasi konvensional seperti tabungan atau deposito di bank. para investor saat ini mulai tertarik untuk menanamkan modalnya melalui pembagian kepemilikan perusahaan yang ditandai dengan surat berharga yang disebut saham. proses investasi ini dilakukan dengan cara jual beli sejumlah saham yang akan menentukan persentasi kepemilikan seorang investor terhadap perusahaan yang bersangkutan. proses jual beli tersebut dilakukan dengan cara lelang di suatu tempat perdagangan khusus yang disebut dengan bursa saham atau pasar modal (haryadi, 2013). kalangan umum maupun profesional masih banyak yang melakukan analisis fundamental secara manual dimana hal itu akan memakan waktu yang lama dan kurang efektif dalam mengolah data saham yang sangat banyak jumlahnya. analisis fundamental memerlukan pemahaman beberapa teknik dan teori, serta sulit dilakukan oleh orang awam (fahrurrozy, 2006; http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 3 juni 2019 114 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional falani, sugiono, & junaedi, 2012; soemapradja, logahan, & ongowarsito, 2014). permasalahan yang terjadi pada saat penyeleksian saham adalah keterbatasan kemampuan sumber daya manusia dalam hal ini bagian admin dalam mencari kriteria-kriteria yang diinginkan dalam waktu yang lebih singkat (fahrurrozy, 2006; falani et al., 2012). oleh karena itu diperlukan pengembangan suatu perangkat lunak yang dapat mempercepat pengambilan keputusan dalam memilih saham prima. pada penelitian ini dikembangkan sebuah sistem pendukung keputusan menggunakan metode simple additive weighting (saw). metode ini dipilih karena mampu menentukan nilai bobot untuk setiap atribut, kemudian dilanjutkan dengan proses perankingan yang akan menyeleksi alternatif terbaik dari sejumlah alternatif. dalam hal ini, alternatif yang dimaksud adalah saham prima berdasarkan kriteria-kriteria yang ditentukan. metode saw sering dikenal dengan istilah penjumlahan terbobot. konsep dasar metode simple additive weighting (saw) adalah mencari penjumlahan terbobot dari rating kinerja pada setiap alternatif pada semua atribut (kusumadewi, 2003). metode saw membutuhkan proses normalisasi matrik keputusan (x) ke suatu skala yang dapat diperbandingkan dengan semua rating alternatif yang ada. sistem pendukung keputusan yang dikembangkan, diterapkan untuk menyeleksi saham prima pada cv. bintang semesta. metode ini dipilih karena mampu menyeleksi alternatif terbaik dari sejumlah anternatif. dalam hal ini alternatif yang dimaksud adalah saham-saham yang terdaftar di bursa efek indonesia (bei). penelitian dilakukan dengan mencari penjumlahan terbobot dari nilai yang didapat pada setiap alternatif kemudian dilakukan proses perangkingan yang akan menentukan alternatif yang optimal yaitu saham prima. berdasarkan penelitian pada jurnal yang berjudul sistem pendukung keputusan penilaian proses belajar mengajar menggunakan metode simple additive weighting (saw) (usito, 2013), penulis menggunakan metode yang sama yaitu metode simple additive weighting (saw), namun diterapkan pada objek penelitian yang berbeda dan data yang berbeda pula. pada penelitian sebelumnya (usito, 2013), metode saw diterapkan di bidang pendidikan, sedangkan pada penelitian ini diterapkan pada data saham. tabel 1. rangkuman penelitian terkait no. paper tujuan penelitian metode kriteria 1 (yobioktabera, susanto, & wijayanti, 2012) untuk mengetahui pattern minat suatu sekolah atau institusi pendidikan terhadap jenis artikel tertentu simple additive weighting sistem pendukung keputusan yang dibangun ini berguna untuk mengetahui pattern minat suatu sekolah atau institusi pendidikan terhadap jenis artikel tertentu. 2 (usito, 2013) penilaian proses belajar mengajar yang dilakukan oleh dosen. simple additive weighting kriteria: tingkat kehadiran mengajar, ketepatan memulai dan mengakhiri kuliah, kesesuaian materi dengan silabus, kemudahan penyampaian materi untuk dipahami, memotivasi belajar dalam mendalami mata kuliah. 3 (oktaputra & noersasongko, 2014) spk kelayakan pemberian kredit motor pada perusahaan leasing. simple additive weighting kriteria: kepribadian, uang muka, kemampuan, jaminan, kondisi 4 (pohan & wibowo, 2017) spk pemilihan vendor pada pt. samudera indonesia ship management fuzzy-anp & topsis kriteria: delivery, price, quality, service 5 (prayogo, 2018) spk pemilihan karyawan teladan pt. bank rakyat indonesia simple additive weighting kriteria: absensi, produktivitas, tugas individual, tanggung jawab, penilaian supervisor 6 (bunajjar & solichin, 2018) rekomendasi lokasi cabang toko untuk gerai pulsa anp & topsis kriteria: price, quality, enviromental, facilities. 7 (mardiana & tanjung, 2019) sistem pendukung keputusan pemilihan perguruan tinggi swasta topsis kriteria: akreditasi, jumlah mahasiswa, jumlah dosen, biaya, fasilitas, jumlah jurusan. hasil penelitian ini dapat berguna untuk memilih alternatif yang terbaik untuk mendapatkan saham prima. dengan demikian, para investor yang akan berinvestasi di saham, tidak http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 3 juni 2019 p-issn: 2656-1743 e-issn: 2656-1735 115 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional akan salah membeli saham karena sudah memiliki daftar nama-nama saham prima. metode penelitian langkah penelitian untuk menyelesaikan permasalahan, dalam penelitian ini dilakukan beberapa langkah dan metode penelitian, sebagai berikut: a. studi pustaka metode ini dilakukan untuk mengumpulkan data dengan mencari dan membaca buku-buku referensi, jurnal, paper dan karya ilmiah lainnya yang dapat menunjang penelitian ini. b. analisis dokumen dokumen yang diperoleh kemudian dipelajari dan dianalisis untuk mengetahui bentuk sistem cara kerja yang akan dibangun. c. rancangan sistem metode ini dilakukan dengan membuat rancangan layar, flowchart, database dan lainlain sesuai dengan hasil analisis. d. implementasi rancangan sistem yang sudah dibuat akan diimplementasikan berdasarkan hasil analisis. kemudian hasil analisa akan dituangkan dalam kode-kode dengan menggunakan bahasa pemrograman tertentu. e. uji coba sistem setelah sistem selesai dibangun, maka dilakukan uji coba terhadap sistem yang dibangun. pengujian dilakukan dengan metode black box. teknik analisis data metode simple additive weighting (saw) sering dikenal dengan istilah metode penjumlahan terbobot. konsep dasar metode simple additive weighting (saw) adalah mencari penjumlahan terbobot dari rating kinerja dari masing-masing alternatif pada semua atribut. metode simple additive weighting (saw) membutuhkan proses normalisasi matriks keputusan (x) ke suatu skala yang dapat diperbandingkan dengan semua rating alternatif yang ada. kriteria-kriteria yang dibutuhkan salah satunya adalah laba bersih, laba usaha, pendapatan dan per, penentuan kriteria dapat digolongkan ke dalam 2 kriteria : a. benefit benefit adalah nilai maksimum dari suatu kriteria. adapun kriteria yang dapat digolongkan ke dalam kriteria benefit adalah pendapatan, laba kotor, laba usaha, laba bersih, aset. b. cost cost adalah nilai minimum dari suatu kriteria. adapun kriteria yang dapat digolongkan ke dalam kriteria cost adalah per. terdapat 4 tahapan yang harus dilakukan pada metode simple additive weighting (saw) dan diterapkan pada penelitian ini, yaitu: a. pengumpulan kriteria tabel 2 menyajikan kriteria yang digunakan untuk seleksi saham prima. selain itu, ditetapkan skala pembobotan seperti pada tabel 3. tabel 2 tabel kriteria kriteria keterangan c1 pendapatan c2 laba kotor c3 laba usaha c4 laba bersih c5 aset c6 per tabel 3 skala pembobotan skala pembobotan bobot cukup 5 rendah 2.5 sangat rendah 1 sangat tinggi 10 tinggi 7.5 b. pembobotan kriteria tabel 4 merupakan tabel pembobotan kriteria yang berguna untuk menampung data-data pembobotan kriteria yang sudah dipilih oleh admin. tabel 4 contoh pembobotan kriteria alternatif kriteria c1 c2 c3 c4 c5 c6 a1 5 2.5 2.5 2.5 5 2.5 a2 2.5 1 1 1 7.5 10 a3 10 1 10 10 10 1 a4 2.5 1 2.5 2.5 2.5 1 a5 10 7.5 5 7.5 7.5 5 a6 7.5 2.5 5 2.5 5 10 keterangan : a1 = adro a2 = born a3 = bumi a4 = brau a5 = atpk a6 = ptba c1 = aset (benefit) c2 = laba bersih (benefit) c3 = laba kotor (benefit) c4 = laba usaha (benefit) c5 = pendapatan (benefit) c6 = per (cost) c. matrik keputusan matrik keputusan dibuat untuk melakukan normalisasi data pembobotan setiap alternatif. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 3 juni 2019 116 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional normalisasi dipisahkan antara kriteria yang bersifat benefit dan cost. d. perankingan hasil normalisasi selanjutnya diranking dengan mengurutkan dari nilai terbesar ke nilai terkecil. hasil penelitian dan pembahasan desain sistem implementasi merupakan salah satu tahapan dalam pembuatan program. sistem pendukung keputusan ini dibangun dengan menggunakan bahasa pemrograman java dan basis data menggunakan mysql. berikut ini beberapa tampilan layar sistem pendukung keputusan yang telah dikembangkan dalam penelitian ini. gambar 1. tampilan form data saham gambar 2. tampilan form data kriteria gambar 1 adalah tampilan form data saham. pada menu ini dapat mengubah dan menghapus data saham dengan cara pilih salah satu data yang berada di dalam tabel. sementara itu, gambar 2 menampilkan form data kriteria untuk menambahkan, mengubah dan menghapus data kriteria. bobot kriteria dapat dikelola melalui halaman data bobot (gambar 3). di halaman ini, pengguna dapat menambahkan, mengubah dan menghapus data bobot. gambar 3. tampilan from data bobot gambar 4 menyajikan tampilan layar analisis saham. pada menu ini, pengguna dapat melakukan analisis saham dengan menentukan bobot pada masing-masing kriteria. kriteria yang digunakan adalah aset, laba bersih, laba kotor, laba usaha, pendapatan dan per. gambar 4. tampilan halaman input analisis saham hasil analisis saham ditampilkan pada gambar 5. pada menu ini, pengguna dapat melihat hasil dari pemilihan saham. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 3 juni 2019 p-issn: 2656-1743 e-issn: 2656-1735 117 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional gambar 5. tampilan hasil analisis saham gambar 6. tampilan hasil analisis saham dalam bentuk grafik selain dalam bentuk tabel, sistem juga mampu menampilkan hasil analisis dalam bentuk grafik seperti disajikan pada gambar 6. untuk pengolahan lebih lanjut, sistem juga dapat menampilkan hasil analisis dalam bentuk microsoft excel. pengujian sistem pada penelitian ini dilakukan pengujian sistem dengan metode pengujian black box. pengujian bertujuan untuk mengetahui fungsionalitas dari sistem atau aplikasi yang dihasilkan. tabel 5 menyajikan cuplikan hasil pengujian perangkat lunak dengan metode black box. berdasarkan hasil pengujian, sistem pendukung keputusan yang dibangun dapat berjalan dengan baik. tabel 5. hasil pengujian sistem dengan blackbox # modul fungsionalitas hasil 1 login menginputkan username dan password dengan benar berhasil masuk ke halaman pengguna 2 login menginputkan username dan/atau password yang salah menampilkan pesan gagal 3 data saham menambahkan, mengubah dan menghapus data saham berhasil tersimpan di db dan tampil di layar 4 data kriteria menambahkan, mengubah dan menghapus data kriteria berhasil tersimpan di db dan tampil di layar 5 analisis saham menjalankan modul analisis data saham berhasil ditampilkan hasil perhitungan dan perangkinan saham dalam bentuk tabel dan grafik 6 analisis saham mengekspor data hasil analisis ke file ms excel berhasil menyimpan ke file dan dapat dibuka dengan program ms excel simpulan simpulan berdasarkan penelitian yang telah dilakukan, dapat ditarik beberapa kesimpulan, antara lain: 1) permasalahan dapat diselesaikan dengan mengimplementasikan sistem pendukung keputusan dengan metode simple additive weighting (saw). 2) aplikasi ini dibangun sebagai alat bantu bagi cv. bintang semesta untuk memilih alternatif yang terbaik untuk mendapatkan saham prima. 3) hasil akhir dari perhitungan simple additive weighting (saw) ini berupa diagram batang dan dapat dieksport ke microsoft excel. 4) berdasarkan hasil pengujian fungsionalitas dengan metode pengujian black box disimpulkan bahwa aplikasi dapat berjalan dengan baik dan dapat menampilkan hasil analisis saham prima bagi penggunanya. saran selain menarik beberapa kesimpulan, peneliti juga memberikan saran dalam penerapan aplikasi sistem pendukung keputusan yang telah http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 3 juni 2019 118 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional dihasilkan dalam penelitian ini. spesifikasi kebutuhan perangkat keras dan perangkat lunak harus dipenuhi agar aplikasi dapat bekerja dengan baik dan optimal. selain itu, penelitian ini dapat dikembangkan untuk menyelesaikan permasalahan di bidang lain. daftar referensi bunajjar, k., & solichin, a. (2018). determining the location of a wholesale pulse business branch with anp and topsis methods. international journal of advanced studies in computer science and engineering (ijascse), 7(11), 1–5. fahrurrozy. (2006). sistem penunjang keputusan investasi saham pada bursa efek jakarta. uin syarif hidayatullah. falani, a. z., sugiono, j. p., & junaedi, h. (2012). sistem pendukung keputusan investasi saham berbasis fuzzy logic. in proceeding seminar nasional fakultas teknik (snft) (hal. b-1-b-9). universitas muhammadiyah sidoarjo. haryadi, r. (2013). start up trader : jangan jadi trader sebelum baca buku ini ! visimedia pustaka. kusumadewi, s. (2003). artificial intelligence (teknik dan aplikasinya). yogyakarta: graha ilmu. mardiana, t., & tanjung, s. s. (2019). sistem pendukung keputusan pemilihan perguruan tinggi swasta menggunakan topsis. jurnal riset informatika, 1(2), 25–34. oktaputra, a. w., & noersasongko, e. (2014). sistem pendukung keputusan kelayakan pemberian kredit motor menggunakan metode simple additive weighting pada perusahaan leasing hd finance. program studi sistem informasi. universitas dian nuswantoro. pohan, f., & wibowo, a. (2017). integrasi model pendukung keputusan evaluasi pemilihan vendor dengan fuzzy analytical network process dan topsis studi kasus pt. samudera indonesia ship management. jurnal teknik, 6(2), 83–91. prayogo, j. (2018). sistem pendukung keputusan karyawan teladan pt. bank rakyat indonesia dengan metode simple additive weighting. jurnal riset informatika, 1(1), 35– 42. soemapradja, t. g., logahan, j. m., & ongowarsito, h. (2014). pengembangan aplikasi simulasi perdagangan saham dengan sector rotation dan linear programming. binus business review, 5(1), 418–428. usito, n. j. (2013). sistem pendukung keputusan penilaian proses belajar mengajar menggunakan metode simple additive weighting (saw). universitas diponegoro semarang. https://doi.org/10.1017/cbo978110741532 4.004 yobioktabera, a., susanto, h., & wijayanti, s. (2012). perancangan e-learning cerdas berbasis dss dengan menggunakan metode simple additive weighting pada smp n 9 semarang, 2012(semantik), 444–447. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 51 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. implementasi self-regulated learing pada aplikasi pembelajaran manajemen proyek sistem informasi pada perguruan tinggi swasta x di jakarta kelvin febrianto1, yunus fadhillah2 program studi teknik informatika institut bisnis dan informatika kwik kian gie 156140275@student.kwikkiangie.ac.id, 2yunus.fadhillah@kwikkiangie.ac.id abstrak pengerjaan proyek sistem informasi masih mengalami kegagalan dan kerugian dalam beberapa tahun belakangan ini. maka dari itu pemahaman konsep manajemen proyek haruslah diajarkan dalam perkuliahan. dari hasil analisa perkuliahan yang diadakan pada perguruan tinggi swasta x di jakarta selama sepuluh tahun silam ini menunjukkan kesenjangan antara hasil belajar harian dengan nilai ujian yang mahasiswa dapatkan. sehingga harus ada sebuah proses belajar baru yang memperkuat pemahaman mahasiswa terhadap konsep manajemen proyek. metode self-regulated learning (srl) berfokus pada pembelajaran mandiri melalui metakognisi, motivasi, pengaturan diri, dan evaluasi diri. untuk mendorong proses belajar tersebut membutuhkan sebuah alat bantu dalam proses belajar. spesifikasi alat belajar tersebut membutuhkan terciptanya proses metakognisi dengan mengarahkan langkah-langkah belajar secara jelas dan memotivasi siswa dengan penggunaan alat belajar yang intuitif. hasilnya adalah software belajar yang secara eksplisit membantu proses belajar dengan menghasilkan dokumen proyek untuk membantu pemahaman konsep manajemen proyek dan antarmuka pengguna yang interaktif dan mudah digunakan untuk memotivasi proses belajar. kata kunci: manajemen proyek, sistem informasi, pembelajaran berbasis siswa, self-regulated learning , proses pembelajaran abstract failing it projects has kept growing over the past recent years. understanding of project management concepts must be taught in college. recent studies at the conducted courses at college x in jakarta over the past ten years has shown discrepancy between daily exercises with the exam result students received. therefore, developing a new learning process is required to enhance the student’s understanding of project management concepts. self-regulated learning method encompasses independent learning by metacognition, motivation, self-regulation, and self-evaluation. to develop such process would require a learning tools during the learning process. the technical specification for the learning tools in question needs to enable metacognition process by directing the students towards the learning steps and motivates the students by intuitive use of learning tools. the results is a learning software that explicitly help the learning process by generating project documents to help understanding project management concept and interactive user interface that is easy to use and motivates the learning process. keywords: project management, information system, student centered learning, self-regulated learning, learning process. pendahuluan beberapa tahun belakangan ini banyak sekali investasi terhadap proyek-proyek it yang mengalami kegagalan pada saat perencanaan ataupun pada saat implementasi proyek tengah berjalan (marchewka, 2014). hal ini tidak hanya merugikan investor proyek tetapi juga berdampak pada kepercayaan publik terhadap keberhasilan investasi proyek sistem informasi (straub, kerlin, & whalen, 2017). melihat hal ini mendorong keharusan agar manajemen proyek dikuasai oleh mahasiswa dalam studi s1 teknik informatika dan sistem informasi. akan tetapi hasil studi perkuliahan manajemen proyek sistem informasi (mpsi) di perguruan tinggi swasta x di jakarta dalam sepuluh tahun belakangan ini menunjukkan kesenjangan antara hasil belajar harian dengan http://creativecommons.org/licenses/by-nc/4.0/ mailto:56140275@student.kwikkiangie.ac.id mailto:yunus.fadhillah@kwikkiangie.ac.id issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 52 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. nilai ujian yang mahasiswa dapatkan. gambar 1 dan 2 menunjukkan grafik dari perkuliahan ratarata manajemen proyek sistem informasi yang berlangsung di perguruan tinggi swasta x di jakarta selama sepuluh tahun silam. dengan menghilangkan semua asumsi seperti pengaruh dari kemampuan mengajar dosen, kemampuan mahasiswa menerima materi, perubahan kurikulum, pembobotan nilai, dan lain-lain. terdapat penurunan nilai akhir yang cukup terlihat dalam beberapa tahun belakangan ini. penyebabnya dapat terlihat pada nilai uts yang cukup rendah dan nilai uas yang hampir sama rendahnya. akan tetapi terdapat kejanggalan ketika hasil ujian tersebut dibandingkan dengan hasil nilai harian. ini menunjukkan kejanggalan dalam kinerja harian mahasiswa dibandingkan ujian mereka. oleh karena itu proses belajar manajemen proyek harus ditingkatkan. sumber: (febrianto & fadhillah, 2018) gambar 1. nilai akhir rata-rata perkuliahan mpsi di pts x, jakarta sumber: (febrianto & fadhillah, 2018) gambar 2. nilai harian perkuliahan mpsi di pts x, jakarta ranah konsep manajemen proyek konsep manajemen proyek yang diajarkan pada pts x di jakarta mengacu pada buku panduan project management body of knowledge (pmbok) (project management institute, 2017) di dalam panduan pmbok terdapat 10 ranah konsep dari manajemen proyek yang dibagi menjadi 49 proses dan dikelompokkan ke dalam 5 tahapan proses yaitu: (1) inisiasi; (2) perencanaan; (3) eksekusi; (4) pengawasan; dan (5) penutup; penjabaran lengkap dari proses-proses tersebut dapat dilihat pada lampiran tabel i. sistem perkuliahan yang berjalan sumber: (febrianto & fadhillah, 2018) gambar 3. proses perkuliahan mpsi di pts x jakarta pada gambar 5 di atas, pembelajaran merupakan gabungan antara mata kuliah yang disusun sesuai dengan silabus rencana perkuliahan, jadwal pertemuan, dan total kelas yang diajarkan dengan dosen pengajar yang mengajar di perguruan tinggi swasta x di jakarta. setelah melewati proses pembelajaran, mahasiswa kemudian diarahkan untuk menghasilkan output pembelajaran mereka selama berkuliah, seperti tugas harian, uts dan uas. ceramah materi kuliah latihan dalam kelas tugas harian sumber: (febrianto & fadhillah, 2018) gambar 4. proses pembelajaran dalam kelas dalam kelas perkuliahan mahasiswa menerima ceramah konsep soal teori manajemen proyek sesuai dengan rencana perkuliahan. konsep tersebut kemudian diperkuat dengan latihan dalam kelas dan tugas harian. tugas harian yang diberikan merupakan implementasi dari konsep manajemen proyek yang dalam hal ini adalah dokumen proses manajemen proyek dengan urutan sebagai berikut: 0,00 10,00 20,00 30,00 40,00 50,00 60,00 70,00 80,00 90,00 100,00 0 10 20 30 40 50 60 70 80 90 100 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 53 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. project charter daftar stakeholders work breakdown structure gantt chart biaya proyek daftar komunikasi proyek penutup proyek sumber: (febrianto & fadhillah, 2018) gambar 5. alur dokumen tugas harian metode penelitian metodologi penelitian untuk menemukan solusi dari permasalahan proses belajar adalah sebagai berikut: metode self-regulated learning metode self-regulated learning adalah metode belajar mandiri dengan terus melakukan penyesuaian terhadap hasil belajar yang dicapai dengan tujuan akhir dari proses belajar melalui perencanaan, pengaturan, dan evaluasi (nilson, 2013) (kizilcec, pérez-sanagustín, & maldonado, 2017) . metode srl terdiri dari 4 parameter yaitu: (1) metakognisi; (2) motivasi; (3) pengaturan diri; dan (4) evaluasi diri; yang direpresentasikan dengan gambar berikut: sumber: (febrianto & fadhillah, 2018) gambar 6. komponen-komponen dalam self-regulated learning manfaat dari metode srl adalah peningkatan dalam performa belajar, percaya diri bertambah, kesadaran akan kemampuan diri, pengendalian stress, dan manajemen diri yang lebih baik (nilson, 2013). melihat akan manfaatnya dan kegunaannya dalam perkuliahan. membuat metode ini sangat cocok untuk menjadi pendekatan utama dalam merancang proses belajar tambahan yang mengkomplemen sistem perkuliahan yang ada dengan harapan mampu meningkatkan peforma perkuliahan manajemen proyek sistem informasi di pts x jakarta. spesifikasi teknis hasil wawancara dengan mahasiswa-mahasiswa yang pernah mengambil mata kuliah manajemen proyek sistem informasi, mengatakan bahwa dikarenakan tidak adanya langkah yang jelas dalam belajar membuat motivasi mereka cukup lemah selama berkuliah. langkah yang jelas dalam belajar dapat diukur sebagai parameter metakognisi, sedangkan motivasi belajar diukur sebagai motivasi dalam srl. dengan demikian mendorong adanya kebutuhan untuk mengembangkan alat bantu belajar dalam bentuk e-learning (clark & mayer, 2016) yang dapat memberikan metakognisi dan motivasi selama proses belajar berlangsung. sumber: (febrianto & fadhillah, 2018) gambar 7. rancangan proses belajar yang diusulkan e-learning akan diimplementasi pada platform web untuk memanfaatkan segala kelebihan yang ditawarkan oleh web ketimbang oleh desktop (broadbent & poon, 2015). tidak hanya itu spesifikasi kebutuhan software lebih lanjut adalah sebagai berikut: berjalan pada platform web. mengarahkan mahasiswa dalam langkahlangkah pembuatan dokumen proyek. http://creativecommons.org/licenses/by-nc/4.0/ issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 54 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. rancangan antarmuka akan mengacu kepada 8 golden rules of interface design (shneiderman, plaisant, cohen, jacobs, & elmqvist, 2016) dokumen proyek dalam proses belajar mencakup (1) project charter; (2) daftar stakeholders; (3) gantt chart; (4) wbs; (5) biaya proyek; (6) komunikasi proyek; dan (7) penutup proyek; dokumen proyek dalam proses akan dihasilkan dalam format .pdf. membangkitkan motivasi belajar. metode rapid application development dengan spesifikasi software tersebut maka metode rapid application development (rad) dipilih sebagai metode pengembangan software web belajar. metode rad terdiri atas 4 proses yaitu: (1) analisa kebutuhan; (2) rancangan software; (3) coding; serta (4) perpindahan cepat (cutover); dalam rentang waktu yang cukup singkat yang disebut juga dengan timebox (isaias & issa, 2015) sumber: (febrianto & fadhillah, 2018) gambar 8. framework sdlc rapid application development metode sdlc ini dianggap sesuai untuk pengerjaan software dikarenakan tingkat kesulitan dari web belajar cukup sederhana, dan waktu pengerjaan yang relatif singkat. maka dari itu timebox untuk pengerjaan metode rad sendiri akan berkisar sekitar 2-3 minggu. dengan estimasi jumlah timebox yang akan digunakan sebanyak 2 timebox. hasil penelitian dan pembahasan hasil dari rancangan software adalah sebuah web belajar yang dapat diakses dengan menggunakan browser baik secara lokal maupun online dengan rancangan tampilan yang mengikuti pedoman 8 golden rules of interface design (shneiderman et al., 2016). tidak hanya itu web juga mampu melakukan proses pembuatan dokumen manajemen proyek dengan mengandalkan input dari pengguna serta mampu menyimpan data tersebut ke dalam browser. analisis dari implementasi software belajar mengacu kepada spesifikasi software yang telah ditetapkan sebelumnya. beberapa dari spesifikasi tersebut pada tabel 1 berikut: tabel 1. implementasi spesifikasi website belajar spesifikasi website belajar status implementasi berjalan pada platform web. sudah terimplementasi dokumen proyek dalam proses akan dihasilkan dalam format .pdf. sudah terimplementasi dokumen proyek dalam proses belajar mencakup (1) project charter; (2) daftar stakeholders; (3) gantt chart; (4) wbs; (5) biaya proyek; (6) komunikasi proyek; dan (7) penutup proyek; sudah terimplementasi sumber: (febrianto & fadhillah, 2018) untuk lebih lanjut lagi ada beberapa spesifikasi lainnya yang membutuhkan pembahasan lebih mendalam di antaranya adalah: mengarahkan mahasiswa dalam langkahlangkah pembuatan dokumen proyek website alat belajar diawali dengan halaman dashboard yang informatif, dengan memberikan penjelasan sekilas perihal dokumen proyek yang dapat dibuat dan dengan alur halaman web yang sederhana membuat langkah-langkah pembuatan dokumen terarah dengan baik. rancangan antarmuka mengacu kepada 8 golden rules of interface design berikut adalah implementasi rancangan antarmuka dikaitkan dengan 8 aturan emas rancangan antarmuka (shneiderman et al., 2016) tabel 2. kriteria 8 aturan emas rancangan antarmuka dan status implementasinya 8 aturan emas rancangan antarmuka website belajar mempertahankan konsistensi. sudah terimplementasi kejar pengunaan secara universal. belum terimplementasi http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 55 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. 8 aturan emas rancangan antarmuka website belajar menawarkan feeback informatif. sudah terimplementasi dialog mengarahkan pada penutupan aksi. sudah terimplementasi mencegah error. sudah terimplementasi memperbolehkan aksi yang reversibel yang mudah. sudah terimplementasi menjaga pengguna dalam kendali. sudah terimplementasi mengurangi beban memori jangka pendek. sudah terimplementasi sumber: (febrianto & fadhillah, 2018) dengan demikian dapat dikatakan bahwa program sudah mengimplementasi 8 aturan emas rancangan antarmuka dengan baik. membangkitkan motivasi belajar dengan langkah-langkah pembuatan dokumen yang terarah dengan baik, maka mahasiswa mampu dengan mudah menetapkan strategi belajar yang cocok untuk mereka gunakan. tidak hanya itu, dengan tampilan sederhana dan menarik pengguna dapat meningkatkan motivasi siswa untuk menggunakan alat belajar. kesimpulan beberapa kesimpulan yang diambil dari penelitian ini adalah mahasiswa dapat memiliki langkah-langkah yang jelas dalam mempelajari manajemen proyek jika mereka diarahkan untuk menyusun langsung dokumen-dokumen manajemen proyek tersebut secara rapi dan terstruktur. alat belajar yang dibangun pada penelitian ini mendukung proses pembelajaran dengan secara eksplisit terlibat dalam proses pembelajaran. dalam hal ini adalah proses pembuatan dokumen manajemen proyek melalui input pengguna. dalam proses pembelajaran perlunya perubahan dalam kurikulum dan penambahan materi praktikum. proses belajar manajemen proyek dapat dibuat menarik dan lebih mudah dipahami mahasiswa dengan membuat proses belajar melalui interaksiinteraksi yang terarah dan panduan yang jelas, disertai dengan estetika tampilan program yang modern, sederhana dan konsisten. referensi broadbent, j., & poon, w. l. (2015). self-regulated learning strategies & academic achievement in online higher education learning environments: a systematic review. the internet and higher education, 27, 1–13. https://doi.org/10.1016/j.iheduc.2015.04. 007 clark, r. c., & mayer, r. e. (2016). e-learning and the science of instruction : proven guidelines for consumers and designers of multimedia learning. new jersey: wiley. febrianto, k., & fadhillah, y. (2018). laporan akhir penelitian implementasi self-regulated learing pada aplikasi pembelajaran manajemen proyek sistem informasi pada perguruan tinggi swasta x di jakarta. jakarta. isaias, p., & issa, t. (2015). high level models and methodologies for information systems. new york, ny: springer new york. https://doi.org/10.1007/978-1-4614-92542 kizilcec, r. f., pérez-sanagustín, m., & maldonado, j. j. (2017). self-regulated learning strategies predict learner behavior and goal attainment in massive open online courses. computers & education, 104, 18–33. https://doi.org/10.1016/j.compedu.2016.1 0.001 marchewka, j. t. (2014). information technology project management : providing measurable organizational value. new jersey: john wiley & sons. nilson, l. (2013). creating self-regulated learners: strategies to strengthen students? selfawareness and learning skills. virginia: stylus publishing, llc. project management institute. (2017). a guide to the project management body of knowledge (pmbok guide) (6th ed.). pennsylvania: project management institute. shneiderman, b., plaisant, c., cohen, m., jacobs, s. m., & elmqvist, n. (2016). designing the user interface : strategies for effective humancomputer interaction (6th ed.). london: pearson. http://creativecommons.org/licenses/by-nc/4.0/ issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 56 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. straub, j., kerlin, s., & whalen, d. (2017). teaching software project management using project based learning (pbl) and group projects. in 2017 ieee international conference on electro information technology (eit) (pp. 016–021). ieee. https://doi.org/10.1109/eit.2017.8053323 http://creativecommons.org/licenses/by-nc/4.0/ 134 application of profile matching algorithm in selection of the best employees in property company laeli nurchasanah1, annisa cintakami firdaus2, desti fitriati3 informatics engineering study program1,2,3 universitas pancasila1,2,3 laelifebry90@gmail.com1, cintakamiannisa@gmail.com2, desti.fitriati@univpancasila.ac.id3 (*) corresponding author abstrak pemberian pengharagaan bagi karyawan yang memiliki kelebihan dan kinerja kerja yang baik merupakan salah satu cara untuk meningkatkan daya saing yang positif antar karyawan di suatu perusahaan. penelitian ini bertujuan untuk mencari keunggulan yang dimiliki setiap karyawan agar dapat mengetahui karyawan yang berprestasi. melalui prestasi dalam dunia kerja dapat menjadi tolak ukur untuk mencari karyawan terbaik yang layak mendapatkan penghargaan. analisa data yang digunakan dalam penelitian ini bersumber dari data penjualan perusahaan properti selama tiga bulan terakhir. penelitian ini menggunakan metode profile matching untuk menentukan karyawan terbaik di perusahaan properti. penelitian dengan ini dilakukan dengan cara membandingkan karyawan satu dengan kandidat karyawan yang lainnya berdasarkan kriteria – kriteria yang telah ditentukan. hasil dari penelitian ini berupa perangkingan yang menunjukan urutan karyawan terbaik yang berhak mendapat penghargaan dari perusahaan. kata kunci: profile matching, sistem pendukung keputusan, gap abstract giving awards to employees who have advantages and good work performance is one way to increase positive competitiveness among employees in a company. this study aims to find the advantages of each employee to find out which employees excel. through achievements in the world of work, it can be a benchmark for finding the best employees who deserve awards. analysis of the data used in this study is sourced from data on sales of property companies for the last three months. this study uses the profile matching method to determine the best employees in property companies. this research was conducted by comparing one employee with another employee candidate based on predetermined criteria. the results of this study are in the form of rankings that show the order of the best employees who are entitled to an award from the company. keywords: profile matching, decision support system, gap introduction human resources are one of the main factors to create an effective and efficient performance in a company (sholihaningtias, 2018). the placement of employees according to their knowledge and skills will improve the performance of the employee (sugiartawan, ardriani, & kusuma, 2021). finding the right person worthy of appreciation is not easy. a person's performance is influenced by many factors such as personality and behavioral factors (herlambang, dewanto, harjanta, & setyawati, 2018) the selection of the best employees aims to increase the competence of employees (idam, junaidi, & handayani, 2019). computerization or the use of computers on a large scale in terms of processing data, one of which is the decision-making process for selecting the best employees can minimize the occurrence of inaccuracies in decision making (fitriana, ripanti, & tursina, 2018). to make a decision, of course, it is necessary to do careful analysis and calculations by predetermined criteria. decision-making is generally done using more than one criterion or even many criteria. therefore, an assessment decision model is needed to make it easier for the assessment team to make decisions about who deserves to be the best employee at property company. the assessment factors that will be carried out include several criteria, including based on discipline, number of absences, accumulation of surveyed consumers, the number of bookings, the number of consumers of credit contracts, and length of work. mailto:laelifebry90@gmail.com1 mailto:cintakamiannisa@gmail.com2 135 the profile matching method is one of the approach methods from several studies in decision support systems (fitriana et al., 2018)). the final result of this method aims to produce data in the final form of ranking (ermawita & fauzi, 2020) with a decision support system, it is hoped that it can support decisions that will be taken by the selection team in a company (wahyudi & utama, 2019). currently, at this property company's marketing performance assessment is still not available. to overcome this problem, manual calculations and systems are made using the profile matching algorithm. this method was chosen in the hope of being able to produce the best data and is also expected to help determine who is the best marketing actor who deserves a reward from the property company. the purpose of the study was to produce a decision support system for selecting the best employees according to predefined criteria. research methods types of research the data obtained in this study is sourced from primary data provided directly by the marketing manager of one of the property companies in indonesia. the data provided is sales data in the last three months (august, september, and october). time and place of research the research was conducted over the last three months from august 2021 to early november 2021. the research was conducted at the marketing office of a property company in cibinong. sales data from the last three months was obtained after the interview ended. decision support system decision support systems (dss) is a part of a computer-based (including knowledge-based) information system that is used to support decisionmaking in an organization or company (wahyudi & utama, 2019). dss by utilizing data and models to identify, solve problems, and make decisions aims to help make better decisions (sutinah, 2017). in general, a decision support system is designed as a support for decision-making in a problem that involves many criteria (fauzi, 2019) the stages of the decision support system are problem definition, collecting data or relevant information elements, processing data into information in the form of graphic and written reports, and determining alternative solutions (can be in percentages). the objectives of dss include helping to solve semi-structured problems, supporting managers in making decisions about a problem, and increasing the effectiveness not the efficiency of decision making. profile matching profile matching is a component that expects an ideal indicator variable level with a base level that should be met or passed by workers (kurnia, 2021). in profile matching, the minimum value for each variable is called the gap value. the smaller the gap value, the greater the weight (herlambang et al., 2018). the profile matching method is commonly used in solving semistructured problems in solving problems of determining the best employees, selecting scholarships, and selecting collaboration partners (indriyani, 2019). procedure the profile matching process includes several stages as follows: 1. investigation of a problem 2. determine criteria, sub-criteria, and values 3. determining the value of each alternative 4. determination of target values 5. determine the gap the gap is the difference in the value obtained from the selection team for employees who are nominated for the best employee (saputra, regasari, & sutrisno, 2017). gap collection for each attribute has a different calculation for each problem. the gap value is obtained from the following formula. gap = value – standard value ..................................... (1) 6. convert gap to the weighted value 7. calculation of core factor and secondary factor in the calculation of the profile matching method, the core factor and secondary factor have different assessment weights (sudarmadi, santoso, & sutrisno, 2017). the core factor is the attribute that takes precedence or is the most prominent in a position (pungkasanti & nurma’arif, 2019). the core factor aspect is estimated to produce optimal performance. the calculation of the core factor is formulated as follows. 𝑁𝐶𝐹 = ƹ𝑁𝐶 ƹ𝐼𝐶 ......................................................................... (2) description : ncf = average core factor nc = total number of core factor values ic = number of aspects core factor (malau, 2020) . 136 the secondary factor is supporting aspects other than those in the core factor (pungkasanti & nurma’arif, 2019). the secondary factor calculation can be seen in the following formula. 𝑁𝑆𝐹 = ƹ𝑁𝑆 ƹ𝐼𝑆 .......................................................................... (3) description : nsf = average value of secondary factor ns = total number of secondary factor scores is = number of aspects of a secondary factor (kusumantara, pamuji, & putri, 2019). 8. sum of core factor and secondary factory value 9. calculation of criteria value 10. determine the total value the calculation of the total value is obtained from the following formula. np = (x) % ncf + (x) % nsf......................................... (4) description: np = total score of criteria nfs = average score secondary factor average nfc = core average factor (x) % = the percent value that input. 11. rank after going through the calculation process above, researchers will get conclusions about the value of several alternatives that have been inputted. the highest scoring alternative will be a priority to choose the best employee and will be entitled to a gift from the property company. data, instruments, and data collection techniques this study uses primary data. the technique of collecting criteria and alternative data that will be used in system testing is obtained by conducting direct interviews with the marketing manager of a property company. for information on sales data for the last three months, it was obtained directly in hardcopy form by the marketing manager of the property company after the interview. data analysis technique the data in this study consisted of quantitative and qualitative data. for qualitative data, researchers convert it into numbers (quantitative data) to make it easier to calculate both manual and system calculations. results and discussion the first step for profile matching is to determine the alternatives and criteria used. alternatives can be seen in table 1. table 1. alternatives alternate code alternative name a1 kahfi a2 hendri a3 surya a4 winda after determining the alternatives, the criteria and values are determined as in table 2. table 2. criteria table 2 contains the type of each criterion specified by the company. the score for the criteria obtained from the property company can be seen in table 3. table 3. criteria value of each alternative criteria alternative kahfi hendri surya winda discipline good excellent enough enough number of absences 1 0 4 3 accumulated consumer survey 15 12 10 20 number of bookings 5 5 5 12 jumlah credit akad consumer 5 4 4 10 long work 7years 7 years 5 years 3 years after knowing the information about the value of each criterion for 4 predefined alternatives. the weight value of the criteria expected by the company can be seen in table 4. table 4. criteria weight value from the company 137 the next step is to determine the value of the core factor and secondary factor. the value can be seen in table 5. table 5. weight of core factor and secondary factor core factor 60% secondary factor 40% the next step is to determine the gap mapping. the results can be seen in table 6. table 6. gap mapping criteria assessment factor weight discipline excellent 5 good 4 enough 3 less 2 ineligible 1 number of absences 0 5 1 3 4 4 6 3 7 9 2 >9 1 accumulated consumer survey >15 5 11 15 4 6 10 3 1 5 2 0 1 number of bookings > 12 5 9 12 4 5 8 3 1 4 2 0 1 number of consumer credit agreements > 9 5 7 9 4 4 6 3 1 3 2 0 1 working period > 6 years 5 5 6 years 4 3 4 years 3 1 – 2 years 2 < 1 year 1 the results of the gap calculation can be seen in table 7. table 7. gap calculation the next step is determining the weight of the gap value based on table 8. table 8. weighted gap value the results can be seen in table 9. table 9. weighted results the next step is to calculate the value of the core factor and secondary factor which is then multiplied directly by the weight. the results can be seen in table 10. table 10. calculation results of core factor and secondary factor 138 employees ncf nsf core factor 60% secondary factor 40% a1 3,6 4,5 2,16 1,8 a2 4 4,5 2,4 1,8 a3 3 5 1,8 2 a4 4,2 4 2,52 1,6 the final assessment calculation is determined using formula 4. the final calculation results can be seen in table 11. table 11. ranking values employees np ranking hendri 4,2 1 winda 4,12 2 kahfi 3,96 3 surya 3,8 4 based on table 11, it is known that the order of employees who deserve to be appreciated are hendri, winda, kahfi, and surya. system result implementation to determine the best employees as shown in figure 1. input the username and password to enter the system. input alternatives, criteria, core factor value, and secondary factor value. figure 1. system main page after successfully inputting the value, click the "continue to process" button. to find out the rankings, click the "save and view ratings" button. figure 2. ranking results figure 2 is the result of the calculation according to the criteria and alternatives that have been determined at the beginning. evaluation result accuracy testing aims to find out how much accuracy the level of the system has been made. for accuracy testing, the results of the decision support system with the profile matching method will be compared between manual calculations and the system. accuracy is determined by the following formula. 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 = 𝑇𝑃+𝑇𝑁 𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁 𝑥 100% ........................... (5) description : tp = true positive tn = true negative fn = false positive fn = false negative the research was conducted using 30 sample data. by using the formula above obtained an accuracy value of 100%. conclusions and suggestions conclusions decision support systems using profile matching algorithms can help the role of property management in objective decision making with more effective time. the implementation of the profile matching method for the selection of the best employee selection at property company obtained excellent results by its accuracy rate of 100%. suggestions in the next research, decision support systems using profile matching algorithms could be created not only to determine the best employees in property companies but also to be applied to other fields to increase the variety of use of profile matching algorithms. reference ermawita, o. :, & fauzi, r. (2020). penerapan metode profile matching pada sistem pendukung keputusan pemilihan dosen terbaik (studi kasus: institut pendidikan tapanuli selatan). jurnal education and development, 8(4), 17–20. https://doi.org/10.37081/ed.v8i4.2050 fauzi, m. (2019). implmentasi metode profile matching pada sistem pendukung keputusan dalam pemberian jabatan kelas pada 139 mahasiswa. jurnal sistem informasi kaputama (jsik), 3(1), 11–17. retrieved from http://www.jurnal.kaputama.ac.id/index.php /jsik/article/view/146 fitriana, j., ripanti, e. f., & tursina, t. (2018). sistem pendukung keputusan pemilihan mahasiswa berprestasi dengan metode profile matching. justin (jurnal sistem dan teknologi informasi), 6(4), 157–164. https://doi.org/10.26418/justin.v6i4.2711 3 herlambang, b. a., dewanto, f. m., harjanta, a. t., & setyawati, v. a. v. (2018). implementation of profile matching methods in a mobile based adolescent nutritional assesment systems. jurnal transformatika, 16(1), 1–13. https://doi.org/10.26623/transformatik a.v16i1.868 idam, f., junaidi, a., & handayani, p. (2019). pemilihan karyawan terbaik menggunakan metode profile matching pada pt. surindo murni agung. jurnal infortech, 1(1), 21–27. https://doi.org/10.31294/infortech.v1i1. 6985 indriyani, f. (2019). penerapan metode profile matching sebagai pendukung keputusan pemilihan jurusan pada smk al hidayah. jurnal riset informatika, 1(2), 35–40. https://doi.org/10.34288/jri.v1i2.31 kurnia, e. r. (2021). sistem pendukung keputusan penetapan dosen pembimbing skripsi menggunakan metode profile matching. jurnal perencanaan, sains dan teknologi (jupersatek), 4(1), 797–805. retrieved from https://www.ejournal.uniks.ac.id/index.php/ jupersatek/article/view/1600 kusumantara, p. m., pamuji, a. r., & putri, d. a. (2019). metode profile matching pada sistem pendukung keputusan seleksi profesi desainer grafis di organisasi konsorsium content maker xyx. scan jurnal teknologi informasi dan komunikasi, 14(1), 39–44. https://doi.org/10.33005/scan.v14i1.1459 malau, y. (2020). sistem pendukung keputusan pemilihan kategori promosi produk menggunakan metode profile matching (studi kasus : minimarket). matrik : jurnal manajemen, teknik informatika dan rekayasa komputer, 19(2), 339–346. https://doi.org/10.30812/matrik.v19i2.67 2 pungkasanti, p. t., & nurma’arif, i. p. (2019). sistem pendukung keputusan seleksi asisten praktikum menggunakan metode profile matching. jurnal transformatika, 16(2), 175– 181. https://doi.org/10.26623/transformatik a.v16i2.1250 saputra, d., regasari, r., & sutrisno. (2017). implementasi metode profile matching untuk seleksi penerimaan anggota asisten praktikum ( studi kasus : laboratorium pembelajaran kelompok praktikum basis data filkom ). jurnal pengembangan teknologi informasi dan ilmu komputer, 1(12), 1804–1812. retrieved from http://jptiik.ub.ac.id/index.php/jptiik/article/view/663 sholihaningtias, d. n. (2018). sistem pendukung keputusan kenaikan jabatan menggunakan metode profile matching. string (satuan tulisan riset dan inovasi teknologi), 2(3), 282–288. https://doi.org/10.30998/string.v2i3.2437 sudarmadi, a., santoso, e., & sutrisno. (2017). sistem pendukung keputusan pemilihan personel homeband universitas brawijaya menggunakan metode profile matching. jurnal pengembangan teknologi informasi dan ilmu komputer, 1(12), 1788–1796. sugiartawan, p., ardriani, n. n. d., & kusuma, i. m. w. (2021). sistem pendukung keputusan kelompok promosi jabatan menggunakan metode profile matching. jurnal sistem informasi dan komputer terapan indonesia (jsikti), 3(4), 36–47. https://doi.org/10.33173/jsikti.116 sutinah, e. (2017). sistem pendukung keputusan menggunakan metode profile matching dalam pemilihan salesman terbaik. informatics for educators and professional : journal of informatics, 2(1), 29–42. retrieved from http://www.ejournalbinainsani.ac.id/index.php/itbi/article/view /590 wahyudi, f., & utama, s. (2019). sistem pendukung keputusan penerimaan dosen baru menggunakan metode profile matching (studi kasus: universitas islam raden rahmat malang). jurnal teknologi terapan: g-tech, 3(1), 168–174. https://doi.org/10.33379/gtech.v3i1.338 395 identification of water turbidity with turbidity sensor based on arduino hafdiarsya saiyar1, mohammad noviansyah2 program studi teknologi komputer1, program studi sistem informasi2 universitas bina sarana informatika hafdiarsya.hyr@bsi.ac.id1, mohammad.mnh@bsi.ac.id2 (*) corresponding author abstrak air merupakan kebutuhan yang penting bagi semua makhluk hidup, terutama manusia. manusia membutuhkan air dengan kualitas yang memenuhi persyaratan fisik, mikrobiologi, kimia, dan radiologi yang terdapat dalam parameter wajib dan parameter tambahan. pemilihan parameter tersebut sangat penting untuk memenuhi persyaratan air yang baik, yaitu tidak berasa, tidak berbau, dan berwarna. sedangkan parameter yang digunakan untuk pengidentifikasian air ada tiga,yakni parameter ph, tingkat kekeruhan, dan parameter suhu. dari permasalahan tersebut penulis meneliti pendeteksian kualitas air, khususnya tentang kekeruhan air. penulis mencoba membuat suatu alat yang mampu mendeteksi tingkat kekeruhan air dengan turbidity sensor sebagai pendeteksi tingkat kekeruhan air, arduino uno sebagai pemroses hasil data yang telah dideteksi, dan lcd 16x2 sebagai penampil hasil pengukuran tingkat kekeruhan yang berupa nilai kekeruhan dan keterangan air yang diujikan. rentang pengukuran yang dapat dideteksi oleh alat ini yaitu dari 0 – 3000 ntu. metode penelitian yang digunakan adalah observasi langsung terhadap objek yang terpilih yaitu dilingkungan rumah penulis serta melakukan studi pustaka yang berkaitan dengan mikrokontroler arduino. tujuan penelitian ini adalah untuk mengetahui dan mendeteksi tingkat kualitas air yang ada di masyarakat. sebagai salah satu tools atau alternatif bagi masyarakat untuk mengetahui atau mendeteksi tingkat kualitas air secara dini. kata kunci: arduino uno, kekeruhan air, lcd, ntu, turbidity sensor abstract water is an important need for all living things, especially humans. humans need water with quality that meets the physical, microbiological, chemical, and radiological requirements contained in the mandatory and additional parameters. the selection of these parameters is very important to meet the requirements of good water, namely tasteless, odorless, and colorless. meanwhile, there are three parameters used for water identification, namely ph parameters, turbidity levels, and temperature parameters. from these problems, the authors examine the detection of water quality, especially water turbidity. the author tries to make a tool that can detect the level of turbidity of water with a turbidity sensor as a detector of the level of turbidity in the water, arduino uno as a processor for the data results that have been detected, and a 16x2 lcd as a display of turbidity level measurement results in the form of turbidity values and descriptions of the water being tested. the measurement range that can be detected by this tool is from 0 – 3000 ntu. the research method used is direct observation of the selected object, namely the author's home environment, and conducting library research related to the arduino microcontroller. the purpose of this study was to determine and detect the level of water quality in the community. as one of the tools or alternatives for the community to find out or detect the level of water quality early. keywords: arduino uno, water turbidity, lcd, ntu, turbidity sensor introduction humans, animals, and plants both need water to grow and develop. however, it certainly requires water with each capacity. to continue to live and develop, humans always need water every day. however, it's not just water that humans need. the water that humans need has a certain standard or quality. good water quality can be seen from various things depending on its use. the water needed for human drinking needs is different in quality from the water used for sanitation needs. according to the regulation of the minister of health number 492/menkes/per/iv/2010 concerning drinking water that is safe for health is if it meets the physical, microbiological, chemical, mailto:hafdiarsya.hyr@bsi.ac.id 396 and radioactive requirements contained in the mandatory and additional parameters. the selection of important parameters in this measurement to meet the requirements of good water, namely, tasteless, odorless, and colored. there are three types of parameters used for water identification, namely, ph parameters, turbidity level parameters, and temperature parameters. (amani & prawiroredjo, 2016). the level of turbidity in the water can raise concerns that in the water used some substances are harmful to the human body and cause disease (sutrino, 2004). turbidity is an optical property of a solution that causes light through it to be absorbed and refracted (kadir, 2013). turbidity is expressed in units of ntu (nephelometric turbidity units) and measured using a standard measuring instrument, namely a turbidimeter (joko, 2010). however, this tool is only owned by certain parties, so the development of various water turbidity measuring instruments is carried out by utilizing electronic circuits (suliyani, suciyati, pauzi, & surtono, 2021). water turbidity is a measure that uses the effect of light as a basis for measuring the state of raw water on the ntu (nephelometric turbidity unit) or jtu (jackson turbidity unit) or ftu (formazin turbidity unit) scale. turbidity of water is expressed in units of turbidity, which is equivalent to 1 mg/liter of sio2. this turbidity is caused by the presence of mixed objects or colloidal objects in the water(manaor, efendi, & informatika, 2017)(effendi, 2003). to make it easier to determine the level of water turbidity, the parameters used are ntu (nephelometer turbidity unit) units. (wardhana, 2004). in this study, the author only discusses the second parameter, namely, the level of water turbidity. water turbidity is a form of measurement of scattered light from the interaction of suspended and dissolved materials in water samples, this is used as an indicator of water quality. (kautsar, rizal isnanto, & didik widianto, 2015). the purpose of this study was to determine and detect the level of water quality in the community. as a tool or alternative for the community to find out or detect the level of water quality early. research methods in collecting data and information, the author uses several research methods, including: 1. observation method the author makes direct observations of the selected object, namely in the author's home environment, where the author observes the types of water that exist in the community where the author lives. 2. literature study conducting library research to support all the collection of the required information. information collection is done by looking for references related to the tools that the author will make. these references are obtained from books, journals, articles, and the internet. a. block diagram picture 1. block diagram the explanation of this tool circuit block is: 1. input this input component is the input component that will be processed. the input components consist of: a. a power supply that supplies +12 volts to the appliance circuit b. turbidity sensor which functions to detect the level of turbidity of water poses 2. process the process is an important component in a tool because it functions as a data manager that has been detected by the sensor which then the processed results will be displayed by the output. in this process, the author uses arduino uno r3. 3. output output is the output of all processes that have been carried out. in this tool, the author uses a 16x2 lcd as the display output of the resulting process. a. schematic of tool circuit power supply (input) turbidity sensor (input) arduino uno r3 (proses) lcd 16 x 2 (output) 397 picture 2. set of tools the circuit schematic consists of a series of inputs, processes, and outputs. the input itself consists of a power supply obtained from a 12-volt adapter and a turbidity sensor which functions as a detector of turbidity in the water. the process in this tool is carried out by arduino uno. arduino uno processes and processes data that has been previously known by the turbidity sensor. which then arduino uno displays the results to a 16x2 lcd. the output circuit consists of a 16x2 lcd which has been connected to i2c. the use of i2c is to simplify the pins that will be connected to the arduino uno. with i2c pins used in arduino uno only 4 pieces, namely the ground pin, vcc, sda, and scl. b. how the tool work 1. power supply picture 3 power supply scheme a power supply is a pin that provides voltage for components or circuits that are connected to arduino. (galih, v., purnomosari, e., 2019). in this tool, the author uses a 12-volt power supply with a scheme like a picture above. this power supply uses a 12 volt 1a ct stepdown type transformer, also uses a 1n5401 diode in the form of a bridge which functions as a full-wave rectifier. 2 capacitors function as voltage filters. and also use a 1n4001 diode so that the output current is 1a. 2. turbidity sensor sensors are generally defined as devices capable of capturing physical (physical) or chemical phenomena and then converting them into electrical signals, either electric current or voltage. physical phenomena that can stimulate sensors to produce electrical signals include temperature, pressure, force, magnetic field, light, and so on. (suryono & pramusinto, 2016) turbidity sensor that can detect water turbidity by reading the optical properties of water due to light and as a comparison of light to be reflected with future light (noor, supriyanto, & rhomadhona, 2019). on the turbidity sensor, that the higher the level of water turbidity will be followed by a change in the sensor output voltage(wadu, ada, & panggalo, 2017). picture 4 turbidity sensor turbidity sensor consists of 2, namely adapter dimension and probe dimension. turbidity sensor works when given a voltage of 5 volts. there are two-pin sockets in the turbidity sensor adapter. the socket pin on the right (as shown above) is connected to the probe which is used to detect the turbidity value. while the socket pin on the left (as shown above) is connected to the ground, vcc, and a0 pins on the arduino uno. after the turbidity value is known, the probe then transmits data to the turbidity sensor adapter which is then sent to arduino uno to be processed and processed. 398 3. arduino uno picture 6 arduino uno arduino is an open-source single-board microcontroller, arduino microcontroller hardware is programmed using a wiring-based programming language based on syntax and libraries.(dinata & sunanda, 2015). arduino uno in this tool is used as a controller and processor of the results of the input. arduino uno consists of an atmega 328 microcontroller circuit and has 20 pins. arduino uno itself can operate in a voltage of 7-12 volts. in this tool, arduino uno functions as a data processor and processor that has been detected by the turbidity sensor. the pins in the turbidity sensor are connected to the ground pin, 5v, and the a0 pin on the arduino uno. which then the results that have been processed are displayed by a 16x2 lcd. 4. output circuit picture 7 output circuit schematic lcd is a tool that serves to display size or number so that it can be seen and known through the crystal screen display (budiyanto, 2012). when the water turbidity data has been detected by the turbidity sensor which is then processed and processed using arduino uno, the data in the form of turbidity numbers and water information are then displayed by a 16x2 lcd. in making this tool the author uses i2c to simplify the pins that will be connected to the arduino uno. with the help of i2c, only 4 pins are used, namely ground, vcc, sda, and scl. flowchart diagram picture 8 flowchart diagram research results and discussion in this section, the author will conduct several test schemes, which consist of input experiments, output experiments, and the results of all experiments or conclusions from these experiments. start turbidity sensor reading water turbidity arduino processes and converts data lcd displays data results finish 399 a. input experiment result table 1 the experiment results of input no voltage water type turbidity arduino ntu description sensor uno 1 5 volt mineral water true true 2,11 sensors and arduino uno are working fine pam water true true 2,40 well water true true 3,20 sand water true true 11,75 groundwater true true 3000 2 12 volt mineral water true true 2,56 sensors and arduino uno are working fine pam water true true 2,86 well water true true 3,35 sand water true true 17,57 ground water true true 3000 table 1, the test results above show that there are several differences in the ntu values of the water tested. the voltage difference between the 5volt adapter and the 12-volt adapter is different. the arduino uno voltage needed is 7-12 volts, based on previous test results arduino uno can still work well with a 5-volt adapter, but the ntu test results are different, with a lower value. this value is lower because the power supply required by arduino uno is less than the recommended voltage limit. and also do not use a voltage that exceeds the required component (more than 12 volts) because it can damage the component. therefore, for more accurate results, it is better to use a voltage source that is needed by the arduino uno, namely 7 to 12 volts. b. experimental results output table 2 output result table water type turbidity arduino ntu lcd description sensor uno mineral water true true 2,56 clear sensors and arduino uno are working fine pam water true true 2,86 clear sensors and arduino uno are working fine well water true true 3,35 clear sensors and arduino uno are working fine sand water true true 17,57 dirty sensors and arduino uno are working fine ground water true true 3000 very dirty sensors and arduino uno are working fine from the test results above, the lcd component that is used as an output can work well according to the program that is input. c. overall experiment result table 3 overall experiment result no voltase water type turbidity arduino ntu lcd description sensor uno 1 5 volt mineral water true true 2,11 cleat sensor, arduino uno and lcd are working fine pam water true true 2,40 cleat well water true true 3,20 cleat sand water true true 11,75 dirty ground water true true 3000 very dirty 2 12 volt air mineral true true 2,56 clear sensor, arduino uno and lcd are working fine air pam true true 2,86 clear well water true true 3,35 clear sand water true true 17,57 dirty ground water true true 3000 very dirty 400 conclusions and suggestions conclusions based on the results of data testing using a water turbidity detector using a turbidity sensor with arduino uno, the design of this tool consists of an input block, a process block, and an output block. the input block consists of a power supply and a turbidity sensor, the process block is carried out by arduino uno and the author's output block uses a 16x2 lcd. the level of water turbidity can be detected using the turbidity sensor, then the data obtained will be processed and processed by arduino uno, which then results in the form of turbidity numbers and water information displayed on a 16x2 lcd. with a water turbidity detector using a turbidity sensor with arduino uno, the level of water turbidity can be known more quickly. suggestions in testing with a water turbidity detector using a turbidity sensor with arduino uno, there are still shortcomings. namely in testing this tool to be more thorough in taking data samples so that the data obtained is more accurate, and this tool should be equipped with a voltage source that does not require direct electrical power such as batteries or power banks to facilitate outdoor use. reference amani, f., & prawiroredjo, k. (2016). id alat ukur kualitas air minum dengan para. journal of jetri, 14, 49–62. budiyanto, s. (2012). sistem logger suhu dengan menggunakan komunikasi gelombang radio. jurnal teknologi elektro, universitas mercui buana, 3, 21–27. https://doi.org/https://dx.doi.org/10.22441 /jte.v3i1.735 dinata, i., & sunanda, w. (2015). implementasi wireless sensor network untukmonitoring parameterenergi listrik sebagaipeningkatan layananbagi penyedia energilistrik. nasional teknik elektro, (1), 83–88. effendi, h. (2003). telaah kualitas air bagi pengelolaan sumber daya dan lingkungan perairan. yoyakarta: kanisius. galih, v., purnomosari, e., & n. (2019). pengantar pratikum mekartronika tekstil. cv. mulia jaya. joko, t. (2010). unit air baku dalam sistem penyediaan air minum (pertama). yoyakarta: garaha ilmu. kadir, a. (2013). panduan praktis mempelajari aplikasi mikrokontroler dan pemrogramannya menggunakan arduino. yoyakarta: andi. kautsar, m., rizal isnanto, r., & didik widianto, e. (2015). 143285-id-sistem-monitoringdigital-penggunaan-dan. teknologi dan sistem komputer, 3(1). manaor, a., efendi, s., & informatika, p. t. (2017). implementasi pengendalian lampu otomatis berbasis arduino menggunakan metode fuzzy logic. jurnal penelitian teknik informatika universitas malikussaleh (techsi). noor, a., supriyanto, a., & rhomadhona, h. (2019). aplikasi pendeteksi kualitas air menggunakan. corel it, 5(1), 13–18. suliyani, n., suciyati, s. w., pauzi, g. a., & surtono, a. (2021). rancang bangun alat ukur kekeruhan air menggunakan fototransistor dan led inframerah berbasis arduino uno. journal of energy, material, and instrumentation technology, 2(2), 30–39. https://doi.org/10.23960/jemit.v2i2.53 suryono, & pramusinto, k. (2016). sistem monitoring kekeruhan air menggunakan jaringan wireless sensor system berbasis web. youngster physics journal, 5(4), 203– 210. sutrino, c. . (2004). teknologi penyediaan air bersih. jakarta: rineka cipta. wadu, r. a., ada, y. s. b., & panggalo, i. u. (2017). rancang bangun sistem sirkulasi air pada akuarium/ bak ikan air tawar berdasarkan kekeruhan air secara otomatis. jurnal ilmiah flash, 3(1), 1–10. retrieved from http://222.124.191.188/index.php/flash/art icle/view/131%0ahttp://222.124.191.188/i ndex.php/flash/article/view/131/74%0ahtt p://www.jurnal.pnk.ac.id/index.php/flash/a rticle/view/131 wardhana, w. a. (2004). dampak pecemaran lingkungan. yoyakarta: andi. jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.155 207 the work is distributed under the creative commons attribution-noncommercial 4.0 international license inventory information system design at pt. arsen kusuma indonesia jakarta dahlia sarkawi1, dani ramdani2, anggi oktaviani3, deny novianti4 administrasi perkantoran, sistem informasi universitas bina sarana informatika www.bsi.ac.id dahlia.dls@bsi.ac.id, denynov.dov@bsi.ac.id sistem informasi, teknik informatika stmik nusa mandiri www.nusamandiri.ac.id 12170497@nusamandiri.ac.id, anggi.aov@nusamandiri.ac.id abstrak sistem informasi inventory adalah sebuah sistem informasi yang menyediakan informasi dari beberapa proses yang meliputi pengadaan barang, pergudangan dan pelaporan. oleh karena itu perlu dibuat suatu aplikasi sistem informasi inventory untuk meningkatkan proses kinerja perusahaan yang semula manual menjadi terkomputerisasi yang akan menghasilkan laporan yang lebih terinci. pembuatan aplikasi ini dilakukan dengan cara pengumpulan data, perencanaan sistem, analisa sistem, perancangan sistem dan database. pembuatan program aplikasi dikembangkan dengan php dan model waterfall serta di uji menggunakan black-box testing. dan diharapkan pembuatan aplikasi ini dapat mempermudah perusahaan dalam mengolah persediaan barang, maka dalam penelitian ini dibuatkan perancangan sistem informasi inventory pada pt. arsen kusuma indonesia jakarta. kata kunci: sistem informasi; persediaan; model waterfall abstract an inventory information system is an information system that provides information from several processes including procurement of goods, warehousing, and reporting. therefore it is necessary to create an inventory information system application to improve the company's performance process which originally became computerized which will result in more detailed reports. the creation of this application is done using data collection, system planning, system analysis, system design, and database. application program creation was developed with php and waterfall model as well as tested using blackbox testing. and it is expected that the manufacture of this application can facilitate the company in processing the inventory of goods, then in this research was made designing inventory information system at pt. arsen kusuma indonesia jakarta. keywords: information systems; inventory; waterfall model preliminary inventory is an activity concerning activities and transactions in and out of goods in a company. because inventory is so important to the company, the existence of an inventory system is needed to facilitate the recording and processing of transactions in and out of goods at the company. (irfana, 2017). inventory is very important for the survival of the company (salangka, 2013), (barchelino et al., 2016). the company must be able to estimate the amount of inventory it has (suharti & fong, 2018). inventories owned by the company should not be too much and also not too little because it will affect the costs that will be incurred for the inventory (salangka, 2013). without an inventory, the entrepreneur will be faced with the risk that his company at one time will not be able to meet customer requirements (banuwati et al., 2015), who require or request goods/services (kushartini & almahdy, 2016). inventory is the stock of goods or storage of goods (stevenson & chuong, 2014). to the number of items stored which will be used later. by designing the system towards a better direction, it is hoped that it can help and facilitate http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.155 jurnal riset informatika vol. 2, no. 4 september 2020 208 the work is distributed under the creative commons attribution-noncommercial 4.0 international license the ongoing system process so that it makes it easier to manage data including processing, compiling, storing, and manipulating data which ultimately produces accurate data that can be used for company needs. (irfana, 2017). an inventory information system was created and developed using the waterfall model (frieyadie, 2015). this system is a unit consisting of components or elements that are linked together to facilitate the flow of information, material, or energy to achieve a goal (palit et al., 2015). for that, the system is said to be a good system with characteristics (hutahaean, 2015) namely: components, system boundaries, external environment, system connectors, system inputs, system outputs, system processors, system objectives. the purpose of this research is to make it easier for companies to process inventory so in this study the inventory information system design at pt. arsen kusuma indonesia jakarta. research methods obtain data by conducting research, directly and indirectly, to get it right using the following data collection model: 1. interview, the author conducts direct interviews with the inventory officer or employee. 2. observation, the researcher made direct observations on the existing inventory system at pt. arsen kusuma indonesia. 3. literature study namely by finding and studying relevant books to provide a better understanding of the topic of writing and enrich the writer's knowledge about computer networks. types of research this study uses a qualitative research method approach, which means that data is all information both oral and written, even in the form of pictures or photos, which contribute to answering research problems as stated in the problem formulation or research focus. (rahardjo, 2011). research target/subject the target of this research is to assist and facilitate the ongoing process of the system to facilitate data management including processing, compiling, storing, and manipulating data which ultimately results in inaccurate data that can be used for corporate purposes. research methodology research is often described as a process of the investigation carried out in a planned, orderly, and systematic manner that aims to find, interpret and revise facts. research stages this research was conducted by implementing it in several stages, namely as follows: 1. literature survey in this initial stage, the researcher collected sources and information related to the research. 2. identification of problems identifying problems to be discussed, relating to the inventory information system design at pt. arsen kusuma indonesia jakarta is based on the sources and information that has been obtained. 3. literature review researchers studied theoretical books about inventory information system design which will be used as a theoretical study in research. the information system development model used is the waterfall model. is the model most widely used for the development stage. this waterfall model is also known as a traditional model or classic model (pressman, 2003). waterfall model (waterfall) is often called a linear sequential model (sequential linear) or classical life flow (classic cycle) " (susilo et al., 2018). research results and discussion the method used in developing this software uses the waterfall model method which is divided into several stages, namely:(agus prayitno, 2015). a. software requirements analysis requirements analysis is a requirement that is needed in designing a system designed by the author, this needs analysis is necessary for designing this proposed system and the needs of this system user. 1. user requirements the inventory application has one user who interacts with the system, namely the warehouse admin section. one user chooses the characteristics of the interaction with different systems and has different information needs, such as the warehouse admin needs scenario: a. provide information about the items needed. b. receive and check requests for goods that have been ordered by the supplier. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.155 209 the work is distributed under the creative commons attribution-noncommercial 4.0 international license c. input reports of incoming goods and goods out of the warehouse to the supplier. 2. system requirements a. users must log in first to be able to access the system by entering their username and password so that the privacy of each user is maintained. b. after the warehouse admin logs in, the warehouse admin can use the incoming goods menu, stock items, demand for goods, incoming and outgoing goods that are in the system according to the level access owned by the warehouse admin. c. the system can store and manage admin data, item data, and reports. d. after the warehouse admin uses the system, it is required to log out so that it can log back in when using the system again. b. design 1. system modeling design the following is a warehouse inventory system software design at pt. arsen kusuma indonesia, which will be described below. a. use case diagram modeling figure 1. use case diagram in figure 1, it is explained that actors have access to log in, manage supplier data, manage goods data, manage incoming goods data, manage outgoing goods data, and manage reports. b. activity diagram modeling figure 2. activity diagram kelola data pegawai figure 2 above, shows the sequence of activities in the process of managing employee data. c. class diagram modeling figure 3. class diagram in figure 3, it is explained that the class diagram connects the existing classes in the design of this system, namely, there are incoming goods, admin, outgoing goods, goods, and also suppliers. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.155 jurnal riset informatika vol. 2, no. 4 september 2020 210 the work is distributed under the creative commons attribution-noncommercial 4.0 international license 2. display interface a. interface form login figure 4. interface form login figure 4 illustrates the display on the login form. b. interface main homepage figure 5. interface main homepage figure 5 illustrates the display on the main homepage. c. interface all data items figure 6. interface all data items figure 6 illustrates the display form all data items. and also can choose to print data, or save data to excel format. d. interface all employee data figure 7. interface all employee data figure 7 illustrates the display on the all employee data page. where here we can see all employee data, admin data, cashier data, and add employee data. e. items out interface figure 8. items out interface figure 8 depicts the goods out page. it is on this page that all outgoing goods data are input. f. period goods report interface figure 9. period goods report interface http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.155 211 the work is distributed under the creative commons attribution-noncommercial 4.0 international license figure 9 illustrates the period goods report page. this report can be printed based on the required period. c. code the following is the source-code for data stocking on the goods in the pt. arsen kusuma indonesia. if(isset($_post['tambah'])){ $kd_pre = $_post['kd_pre']; $kd_trans = $_post['kd_trans']; $kd_barang = $_get['id']; $jumlah = $_post['jumlah']; $subtot = $_post['total']; $stok_barang = $_post['stok']; if($jumlah > $stok_barang){ echo ""; } else{ $sql = "select * from table_pretransaksi where kd_transaks i='$kd_trans' and kd_barang='$kd_barang'"; $query = mysqli_query($con,$sql); $row = mysqli_num_rows($query); $data = mysqli_fetch_assoc($query); if($row > 0){ $jumlah = $data['jumlah'] + $jumlah; $subtot = $data['sub_total'] + $subtot; $value = "jumlah='$jumlah',sub_total='$subtot'"; $statement>update_where_2("table_pretransaksi",$value,"kd_barang",$kd_ barang,"kd_transaksi",$kd_trans,"kasir=kelola_transaksi"); } else{ $values = "'$kd_pre','$kd_trans','$kd_barang','$jumlah','$subtot' "; $statement>insert("table_pretransaksi",$values,"kasir=kelola_transaksi"); } d. testing the test used in this study uses black-box testing, as seen in table 1 below: tabel 1. black-box testing no. form uji skenario uji hasil yang diharapkan hasil pengujian 1 tampilan login mengisi username dan password dengan benar berhasil masuk ke menu utama sukses 2 tampilan menu utama membuka menu barang membuka menu barang keluar distributor muncul form data barang muncul form data barang keluar muncul form distributor sukses 3 tampilan data semua barang membuka menu print data membuka menu export excel muncul form print data muncul form export excel sukses 4 tampilan semua data pegawai membuka menu semua data pegawai membuka menu data admin membuka menu data kasir menambah data pegawai muncul form semua data pegawai muncul form data admin muncul form data kasir data pegawai dapat ditambah sukses 5 tampilan tambah barang menambah data barang data barang dapat ditambah sukses 6 tampilan tambah distributor menambah data distributor data distributor dapat ditambah sukses 7 tampilan barang keluar menambah data barang keluar data barang keluar dapat ditambah sukses 8 tampilan laporan barang periode menampilkan laporan barang periode data laporan barang periode dapat ditampilkan sukses e. support describes the use of the software and hardware used in the proposed system and describes it in the configuration form. generally, in a system that has many problems, especially in its maintenance, a system needs to be redeveloped to support the data processing needs by using hardware and software. hardware is a physical factor of a computer that can work optimally and the better the software, the easier it is to process data. the two supporting suggestions constitute a unity that must support each other so that they can be maximally utilized. a. hardware specifications 1) intel (r) core (tm) i5-8250u processor 2) 4gb memory 3) 1 terabyte hard disk 4) 2 gb shared memory 5) mouse 6) keyboard 7) monitor with a minimum screen resolution of 1024x768. b. software specifications the software used to support the proposed program is a. operating system: windows 10 b. application program: sublime text 3 c. database: mysql; d. web server: apache 2.x e. web browsers: google chrome and mozilla firefox. conclusions and suggestions based on the results of the research that has been done, several conclusions can be drawn, namely: the design of this system is to make it easier for users to control data related to the inventory, such as goods data reports, supplier data, incoming goods data, outgoing goods data, and goods stocks. this system built can accelerate performance in the process of data collection of incoming and outgoing goods that are systemized so that it is easier to find the required data and the existence http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.155 jurnal riset informatika vol. 2, no. 4 september 2020 212 the work is distributed under the creative commons attribution-noncommercial 4.0 international license of this inventory system can reduce paper accumulation. the inventory information system that is built can record order transactions, shipments, incoming and outgoing goods, and payment transactions that are computerized and with reports so that they can find out and provide fast, precise, and accurate information every day. suggestions based on the existing discussion, the authors suggest that the inventory information system is still limited and simple so that in the future it is hoped that it can be developed completely, such as auto increment to fill in item numbers automatically. it is necessary to periodically maintain the hardware and software used. development in terms of programming language, namely from php to mobile programming language. it is hoped that this system will continue to be developed with the addition of useful features and more attractive design for users. there is a need for development and better maintenance of the system that has been created so that the system can be used as needed. maintain good performance that has been achieved and implemented by the company. reference list agus prayitno, and y. s. (2015). the research of negative ion test method for fabric. pemanfaatan sistem informasi perpustakaan digital berbasis website untuk para penulis, 1(1), 1–10. https://doi.org/10.4028/www.scientific.net/ amr.756-759.138 banuwati, n., lau, e. a., & rahmawati, i. (2015). analisis pengendalian persedian bahan baku pada pabrik roti sartika disamarinda. ekonomia, 4(2), 152–155. http://ejurnal.untagsmd.ac.id/index.php/ekm/article/view/120 9 barchelino, r., ekonomi, f., bisnis, d., akuntansi, j., sam, u., & manado, r. (2016). the analysis of psak no.14 application toward inventory recording and valuation method at pt. surya wenang indah manado. analisis penerapan psak… jurnal emba, 837(1), 837–846. https://ejournal.unsrat.ac.id/index.php/emb a/article/view/11812 frieyadie, f. (2015). pembangunan sistem informasi inventory menggunakan linear sequential model untuk peningkatan layanan inventory barang. jurnal techno nusa mandiri, 12(2), 209–114. https://doi.org/10.33480/techno.v12i2.45 1 hutahaean, j. (2015). konsep sistem informasi. deepublish. irfana, d. a. (2017). perancangan sistem informasi persediaan barang (inventory application) berbasis web dan bootstrap css [2017]. http://eprints.umpo.ac.id/3027/ kushartini, d., & almahdy, i. (2016). sistem persediaan bahan baku produk dispersant di industri kimia. jurnal pasti, 10(2), 217– 234. https://publikasi.mercubuana.ac.id/index.ph p/pasti/article/view/1590 palit, r. v, rindengan, y. d. y., & lumenta, a. s. m. (2015). rancangan sistem informasi keuangan gereja berbasis web di jemaat gmim bukit moria malalayang. jurnal teknik elektro dan komputer, 4(7), 1–7. https://doi.org/10.35793/jtek.4.7.2015.104 58 pressman, r. s. (2003). software engineering a practitioner’s aproach fifth edition. mc graw hill. rahardjo, m. (2011). metode pengumpulan data penelitian kualitatif. uin maliki malang. https://www.uinmalang.ac.id/r/110601/metodepengumpulan-data-penelitian-kualitatif.html salangka, e. (2013). penerapan akuntansi persediaan untuk perencanaan dan pengendalian lpg pada pt. emigas sejahtera minahasa. jurnal riset ekonomi, manajemen, bisnis dan akuntansi, 1(3), 1120–1128. stevenson, w. j., & chuong, s. c. (2014). manajemen operasi perspektif asia (9th ed.). salemba empat. suharti, s., & fong, r. (2018). analisis akuntansi persediaan barang dagang pada toko cerose home pekanbaru. bilancia : jurnal ilmiah akuntansi, 2(2), 161– 170. http://www.ejournal.pelitaindonesia.ac.id/oj s32/index.php/bilancia/article/view/60 susilo, m., kurniati, r., & kasmawi, k. (2018). rancang bangun website toko online menggunakan metode waterfall. infotekjar (jurnal nasional informatika dan teknologi jaringan), 2(2), 98–105. https://jurnal.uisu.ac.id/index.php/infotekja r/article/view/171 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.168 1 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. metamorphosis visualization with augmented reality using marker-based tracking bayu bagus kencana1, muhammad fathur prayudha2, budi arifitama3 program studi teknik informatika universitas trilogi bagus.bayu@trilogi.ac.id, faturprayuda@trilogi.ac.id, budiarif@trilogi.ac.id abstrak metamorfosis adalah siklus perkembangan biologis dari pertumbuhan hewan mulai dari penetasan hingga mengalami perubahan. siklus metamorfosis dipelajari dalam pembelajaran untuk siswa di sekolah pada mata pelajaran biologi. sayangnya untuk dapat melihat interaksi siklus metamorfosis hewan, membutuhkan waktu dan menemukan hewan yang ingin diamati. penelitian ini memberikan solusi inovatf dalam menjawab permasalahan yaotu dengan menggunakan augmented reality. teknologi augmented reality memvisualisasikan proses metamorfosis dari hewan kedalam bentuk 4 dimensi sehingga siswa menjadi antusias untuk mempelajari bagaimana proses metamorfosis perubahan hewan. metode marker-based tracking digunakan sebagai pendekatan penyelesaian permasalahan dimana lokasi pola tracking pada marker telah ditentukan terlebih dahulu sebagai tempat kemunculan objek augmented reality. hasil dari penelitian ini menunjukan bahwa dengan menggunakan metode marker-based tracking pembelajaran metamorfosis hewan dapat meningkatkan pemahaman metamorfosis siswa karena lebih interaktif. kata kunci: augmented reality, metamorfosis, marker-based tracking abstract metamorphosis is a cycle of biological animal growth. learning metamorphosis is a part of learning for students in schools specifically in the area of biology subjects. unfortunately, the observing activities take time, and finding an animal specimen is limited to study the metamorphosis cycle. this research proposes an innovative solution to overcome these problems which is the implementation of augmented reality technology. the animal metamorphosis cycle process is visualized into 4-dimensional objects to improve interaction for the student on learning metamorphosis during learning sessions. the marker-based tracking method is used as an approach where the location of the tracking pattern on the marker has been determined in advance as the place where the augmented reality object appears. the results of this study indicate that using a marker-based tracking method can improve students' understanding of metamorphosis. keywords: augmented reality, metamorphosis, marker-based tracking introduction metamorphosis is a physical-biological development process of an animal from birth or hatching to develop into a new form physically. the process that occurs in a complete metamorphosis will experience four stages of growth, starting with eggs, larvae, pupa, and adults, while incomplete metamorphosis undergoes three stages of growth starting with eggs, nymphs, and adults (truman & riddiford, 2019),(gonzalez, jiang, & lowe, 2018),(hammer, mcmillan, & fierer, 2014) of learning to recognize the process of animal change is important for a student, especially in biology subject. the process of learning until now uses video learning media to learn biology (nur & nurdiana, 2019) and resulted in an improvement in cognitive learning for the student, but lack of interaction between the video and the student. textbooks are also used as an approach for learning biology in school (wp & supeno, 2018), the approach using textbook on students for biology learning has been analyzed (cimer & coskun, 2018) and resulted that textbooks are still effective for knowledge transfer but lacks the interaction on the student still resulted in a http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.168 jurnal riset informatika vol. 3, no. 1 december 2020 2 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. problem for improving the learning process of the student. the lack of interaction using books and video learning media from previous research stated makes the learning process less attractive to the student. this research proposes a solution to the problem stated, using augmented reality technology. the use of augmented reality technology for introducing metamorphosis is expected to develop a more attractive and interactive learning process about learning how animal processes can carry out a process of perfect and imperfect metamorphosis. augmented reality is a term to describe the real and virtual world combined to create the illusion that there is no boundary between them (arifitama & syahputra, 2017),(ibáñez & delgado-kloos, 2018). augmented reality technology makes 3d objects that have been created appear to be real(lee, 2012). this technology combines the existing environment in the real world and runs interactively in real-time and creates a mixture between components to be used in three-dimensional media for information and promotion facilities (syahputra & arifitama, 2018). marker-based tracking is used as a marker in this research. marker-based tracking requires a two-dimensional marker that has a unique pattern that will be read by a computer through the camera(gherghina, olteanu, & tapus, 2013),(perwitasari, 2018). users will use a predetermined pattern to be able to display objects and be able to interact with the user through the device. the appearance of animal objects will make students understand how to distinguish between perfect and imperfect metamorphosis change processes. the result of this research that the application of the introduction of the perfect and imperfect metamorphosis process through augmented reality with the marker-based tracking method can help education personnel explain about metamorphosis in a more attractive learning process for the student to understand more clearly. research methods the method used in this research is using the marker-based tracking method(siltanen, 2012). (fleck, hachet, & bastien, 2015). the implementation of the marker-based tracking method in augmented reality requires an image that has a unique pattern to display objects, shown in figure 1. figure 1. marker based tracking mechanism from the image shown in figure 1, the camera will scan the marker created and detected, the desired augmented reality object will appear. the development of augmented reality consists of several development phases which are 3d object design, software development, and augmented reality marker development which uses supporting software namely. sketchup software sketchup is a 3d modeling application that is used for various depictions such as architecture, interior design, video games, and film design (lewis & hampton, 2015). in this research, sketchup is used to create object models for metamorphosis materials as showed in figure 2. figure 2. 3d metamorphosis object modeling unity 3d platform unity 3d is an integrated multi-platform game development technology for game creation(unity technology, 2018), building architecture, and simulation. therefore, this study uses unity to design the display navigation, shown in figure 3. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.168 3 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. figure 3. unity platform vuforia software development kit vuforia or vuforia sdk (software development kit) is a library for building augmented reality applications(simonetti, alexandro; paredes, 2016). to integrate it requires a marker that has been stored in the vuforia database. figure 4. hierarchy of application display design hierarchy is a sequence between components that describes how the system is connected. with this hierarchy, the application display will be seen where on the top frame is the main page which has two menus, namely the perfect menu which will display perfect metamorphosis and has 4 frames and an imperfect menu that will display imperfect metamorphosis which has 3 frames. result and discussion augmented reality implementation vuforia software development kit (sdk) is used to create marker-based tracking and to test the accuracy and accuracy of markers. the image that is used as a marker in this research is shown in figures 5 and 6. figure 5. perfect metamorphosis augmented reality marker figure 6. incomplete metamorphosis augmented reality marker it can be seen in figures 5 and 6 that each marker has a unique pattern that differentiates it from other patterns as a basic marker pattern used for augmented reality. the results obtained through vuforia are that the markers used have a pattern that can be applied to augmented reality with a value of 5 out of 5 and can be seen in figures 7 and 8. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.168 jurnal riset informatika vol. 3, no. 1 december 2020 4 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. figure 7. marker value for perfect metamorphosis figure 8. incomplete metamorphosis marker value the chosen markers are imported to unity for the application development process that has been integrated with vuforia, to implement the perfect and imperfect metamorphosis process application showed in figure 9. figure 9. initial appearance this initial display will direct the user to the perfect and imperfect metamorphosis menu. when the user clicks the perfect metamorphosis button, will be directed into another scene shown in figure 10. figure 10. display of the first process of complete metamorphosis the computer will turn on the camera where the camera will scan the markers that have been prepared, then the 3d augmented reality object consisting of butterfly eggs and leaves. next to the object, a description of the phase that occurs in the object will appear. when the user clicks the home screen button, the user will go back to the main menu shown in figure 9. when the user clicks the next button, the object will change when the user scans the same marker as shown in figure 11 or when the previous button is clicked, the object will appear in figure 13. figure 11. display of the second process of complete metamorphosis in figure 11, the object will change from an egg to a larva. there is a description that explains the larval phase in an object. when the user clicks the next button, the object will change to the next phase in figure 12 or when the user clicks the previous button the object will appear in figure 10. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.168 5 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. figure 12. display of the third process of complete metamorphosis in figure 12, shows the process of changing from a larva into a cocoon. there is a description that explains the cocoon phase. when the user clicks the next button, the object will change to the next phase in figure 13. figure 13. display of the fourth process of complete metamorphosis in figure 13, shows the final process of metamorphosis which is a butterfly. there is a description that explains the final phase. software usability testing software testing is needed as a form of validation regarding the effectiveness of the research. researchers conducted test case validation by distributing test case sheets to 5 application developers. the test case results are as follows : table 1. usability testing no usability test case average result 1 testing movement scene link 80 2 testing the quality of object detection 90 3 testing the stability of object detection 90 4 user interface design 70 5 object visibility 90 6 object detection time responses 80 7 object detection accuracy 80 8 user interface color management 70 9 detailed augmented object 80 10 installation application responses 70 total average 80 based on the results of usability testing performed by the software developer, the average acceptance score is 80, where this value can be concluded that the application is ready for the user. conclusions and suggestions conclusions based on the result, augmented reality can be used to visualize and help educators in explaining the perfect and imperfect of animals’ metamorphosis to the student in a more attractive way. the marker-based tracking used in this research is compatible to be used as a marker. suggestions the suggestions that can be performed for future research are to animate the 3d objects to make it more interactive, the use of different marker like markerless-based tracking to further understand which type of marker is more compatible. reference arifitama, b., & syahputra, a. (2017). cultural heritage digitalization on traditional sundanese music instrument using augmented reality markerless marker method. jurnal teknologi dan sistem komputer. https://doi.org/10.14710/jtsiskom.5.3.2017. 101-105 cimer, a., & coskun, s. (2018). students’ opinions about their ninth grade biology textbook: from the perspective of constructivist http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.168 jurnal riset informatika vol. 3, no. 1 december 2020 6 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. learning approach. journal of education and learning. https://doi.org/10.5539/jel.v7n4p201 fleck, s., hachet, m., & bastien, j. m. c. (2015). marker-based augmented reality. https://doi.org/10.1145/2771839.2771842 gherghina, a., olteanu, a. c., & tapus, n. (2013). a marker-based augmented reality system for mobile devices. proceedings roedunet ieee international conference. https://doi.org/10.1109/roedunet.2013.65 11731 gonzalez, p., jiang, j. z., & lowe, c. j. (2018). the development and metamorphosis of the indirect developing acorn worm schizocardium californicum (enteropneusta: spengelidae). frontiers in zoology. https://doi.org/10.1186/s12983-018-02700 hammer, t. j., mcmillan, w. o., & fierer, n. (2014). metamorphosis of a butterfly-associated bacterial community. plos one. https://doi.org/10.1371/journal.pone.00869 95 ibáñez, m. b., & delgado-kloos, c. (2018). augmented reality for stem learning: a systematic review. computers and education. https://doi.org/10.1016/j.compedu.2018.05. 002 lee, k. (2012). augmented reality in education and training. techtrends. https://doi.org/10.1007/s11528-012-05593 lewis, g. m., & hampton, s. j. (2015). visualizing volcanic processes in sketchup: an integrated geo-education tool. computers and geosciences. https://doi.org/10.1016/j.cageo.2015.05.003 nur, b., & nurdiana, s. (2019). video based learning sebagai media belajar biologi jarak jauh masa kini video-based learning as a present distance learning biology media. in seminar nasional biologi dan pembelajarannya universitas negeri makassar. perwitasari, i. d. (2018). teknik marker based tracking augmented reality untuk visualisasi anatomi organ tubuh manusia berbasis android. intecoms: journal of information technology and computer science. https://doi.org/10.31539/intecoms.v1i1.161 siltanen, s. (2012). theory and applications of marker-based augmented reality. in espoo 2012. vtt science series 3. simonetti, alexandro;paredes, j. (2016). vuforia v1.5 sdk: analysis and evaluation of capabilities. syahputra, a., & arifitama, b. (2018). pengembangan alat peraga edukasi proses siklus air (hidrologi) menggunakan teknologi augmented reality. seminar nasional teknologi dan multimedia (semnasteknomedia), 2-11–1. truman, j. w., & riddiford, l. m. (2019). the evolution of insect metamorphosis: a developmental and endocrine view. philosophical transactions of the royal society b: biological sciences. https://doi.org/10.1098/rstb.2019.0070 unity technology. (2018). unity 3d. in unity technology. wp, h., & supeno, d. (2018). the effectiviness of biology textbook-based mnemonic strategies-assisted method mind mapping against learning retention of students to the study of biology in senior high school. international journal of advanced research. https://doi.org/10.21474/ijar01/6977 http://creativecommons.org/licenses/by-nc/4.0/ lontar template p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 9 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional penerapan metode weighted product sebagai pendukung keputusan seleksi karyawan baru pt. hi-lex indonesia frieyadie1; fariati2 asistem informasi, stmik nusa mandiri jl. damai no. 8, warung jati barat (margasatwa), jakarta 12540, indonesia 1frieyadie@nusamandiri.ac.id (corresponding author) 2fariati1996@gmail.com abstrak penerimaan karyawan dalam setiap perusahaan adalah kegiatan yang senantiasa dilakukan dalam suatu periode tertentu atau secara insidentil. proses perekrutan ini memerlukan proses pengambilan keputusan sebagaimana halnya proses pengambilan keputusan lainnya dalam konteks yang berbeda pada konteks penerimaan karyawan, sejumlah calon karyawan mengajukan diri dengan menyediakan segala berkas yang dipersyaratkan dan mereka juga mungkin diuji secara tertulis atau wawancara. adapun metode yang saya gunakan dalam penelitian ini dengan menggunakan weighted product dan diperhitungkan secara kuantitatif. dari hasil penelitian yang telah dilakukan adalah diperoleh 1 calon karyawan terbaik dari dari jumah sampel sebanyak 10 orang. berdasarkan hasil penelitian yang dilakukan dimana pemilihan bobot penilaian dapat dikembangkan dengan kriteria-kriteria yang lain sesuai dengan kebutuhan perusahaan, pengunaan metode weighted product lebih akurat untuk mendapatkan hasil perhitungan bobot kriteria, hasil perhitungan dengan menggunakan metode weighted product, dengan acuan kriteria tes wawancara, tes psikotes, tes kesehatan, pengalaman kerja, pendidikan terakhir, usia dan penampilan, maka terpilih 1 (satu) orang calon karyawan, yang bernama sukirman yang akan menjadi karyawan di pt.hi-lex indonesia. kata kunci: sistem pendukung keputusan, seleksi karyawan baru, weighted product (wp) abstract acceptance of employees in each company is an activity that is always carried out in a certain period or incidentally. this recruitment process requires a decision-making process as well as other decision-making processes in different contexts. in the context of employee recruitment, a number of prospective employees submit themselves by providing all required files and they may also be tested in writing or interview. the method that i use in this study is using a weighted product and quantitatively calculated. from the results of the research that has been done is obtained the best candidates from 10 households. based on the results of the research conducted where the selection of assessment weights can be developed with other criteria according to company needs, the use of the weighted product method is more accurate to obtain the calculation of criteria weight, the results of calculations using the weighted product method, by reference to interview test criteria, tests psychological test, health test, work experience, recent education, age and appearance, then 1 (one) prospective employee is chosen, named sukirman who will become an employee at pt.hi-lex indonesia. keywords: decision support system, selection of new employees, weighted product (wp) pendahuluan penerimaan karyawan dalam setiap perusahaan adalah kegiatan yang senantiasa dilakukan dalam suatu periode tertentu atau secara insidentil. proses perekrutan ini memerlukan proses pengambilan keputusan sebagaimana halnya proses pengambilan keputusan lainnya dalam konteks yang berbeda. pada konteks penerimaan karyawan, sejumlah calon karyawan mengajukan diri dengan menyediakan segala berkas yang dipersyaratkan dan mereka juga mungkin diuji secara tertulis atau wawancara. pemilihan sejumlah calon karyawan ini terkadang menjadi sesuatu yang sulit dikala jumlah pendaftar itu banyak dari berbagai ragam latar belakang. pt. hi-lex indonesia menyeleksi karyawan baru dari segi tes wawancara, tes psikotes, tes kesehatan, pengalaman kerja, pendidikan terakhir, http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 10 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional usia dan penampilan. saat ini faktor utamanya perusahaan sering kali mendapatkan karyawan yang tidak sesuai dengan bobot yang telah ditentukan disebabkan karena perusahaan tidak memiliki bobot tetap, kesulitan dalam memiliki karyawan yang tidak sesuai dengan kriteria dan masih banyak juga masalah yang lainnya (fajarianto, iqbal, & cahya, 2017) metode weighted product merupakan sebuah metode didalam penentuan sebuah keputusan dengan cara perkalian untuk menghubungkan rating atribut (moenir & budiyanto, 2018), dimana rating setiap atribut harus dipangkatkan terlebih dahulu dengan bobot atribut yang bersangkutan (mirawati, hikmah, & wiguna, 2018). proses admistrasi pada penerimaan karyawan saat ini masih manual (moenir & budiyanto, 2018), (putra & ferdiansyah, 2018) karena perusahaan masih harus memilih curriculum vitae pada masing-masing calon karyawan dan harus mengintputkan data masingmasing calon karyawan satu-persatu kedalam komputer. hal tersebut, terkadang membuat terjadinya subjektifitas (amalia & utami, 2018) pemilihan dan kesalahan pengimputan data (agustin & kurniawan, 2015), (ariani, 2017), maka diperlukan sebuah sistem penudukung keputusan yang dapat digunakan untuk menyeleksi calon karyawan berdasarkan kriteria yang ada dalam menentukan seleksi karyawan (rahmawati & astuti, 2018). data calon karyawan baru belum memiliki kriteria dan bobot yang tepat, proses penerimaan karyawan barunya memerlukan waktu yang cukup lama, dan dalam proses perhitungannya masih belum akurat (ismail & nurjaya, 2016). tujuan penelitian ini diharapkan dapat untuk mendapatkan bobot kriteria kinerja karyawan baru, agar tidak terjadi lagi pemilihan dan kesalahan pengimputan data, dan tidak terjadi lagi kesalahan dalam menginput data karyawan baru metode penelitian tahapan penelitian dalam hal ini akan di uraikan mengenai langkah-langkah yang dilakukan untuk mendapatkan metodologi penelitian yang merupakan suatu tahapan yang harus diterapkan agar penelitian dapat dilakukan dengan terarah dan memudahkan dalam melakukan analisa terhadap permasalahan yang ada. tahapan penelitian tentang sistem pedukung keputusan seleksi karyawan baru di pt. hi-lex indonesia dengan metode weighted product (wp) secara umum dapat digambarkan melalui flowchart dan dapat dilihat pada gambar 1. mulai identifikasi masalah studi pustaka buku teori jurnal terkait menentukan kriteria saran dan kesimpulan mengolah data perhitungan menentukan bobot preferensi mengumpulkan data selesai gambar 1. flowchart tahapan penelitian sumber: hasil pengolahan analisa penulis a. identifikasi masalah mengidentifikasi masalah yang akan dibahas, berkaitan dengan sistem pendukung keputusan seleksi karyawan baru pt. hi-lex indonesia dengan metode weighted product (wp) sesuai dengan informasi yang diperoleh. b. studi pustaka penulis mempelajari buku-buku serta jurnal penelitian sebelumnya yang berkaitan dengan sistem pendukung keputusan metode weighted product (wp). c. mengumpulkan data penulis mengumpulkan data-data dan melakukan wawancara mengenai hal-hal yang berkaitan dengan penelitian. d. menentukan kriteria penulis menentukan kriteria-kriteria dari sistem pendukung keputusan menggunakan metode weighted product (wp) dalam menentukan karyawan baru, diantaranya nilai tes wawancara, tes psikotes, tes kesehatan, pengalaman kerja, pendidikan terakhir, usia dan penampilan e. menentukan bobot preferensi penulis menentukan bobot preferensi atau tingkat kepentingan dari setiap kriteria. f. mengolah data perhitungan penulis mengolah data perhitungan yang sudah di tentukan dengan nilai kriteria dan nilai bobot preferensinya. g. saran dan kesimpulan http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 11 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional penulis mengambil suatu kesimpulan berdasarkan analisis data-data yang terdapat pada pembahasan sebelumnya dan diperiksa apakah kesimpulan sesuai dengan hipotesis, maksud dan tujuan penelitian. selain itu juga memberikan saran yang dapat digunakan sebagai masukan bagi lembaga sekolah terkait untuk dapat dimanfaatkan lebih lanjut. instrument penelitian adapun jenis instrument yang digunakan dalam penelitian ini, yaitu: a. observasi metode ini diterapkan dengan mendatangi obyek perusahaan, yaitu salah satu pt. hi-lex indonesia di tangerang untuk mendapatkan data-data yang dibutuhkan. b. wawancara pengumpulan data dengan cara wawancara adalah usaha untuk mengumpulkan informasi dengan mengajukan beberapa pertanyaan secara lisan kepada hrd. c. studi pustaka metode ini dilaksanakan dengan melakukan studi kepustakaan melalui membaca bukubuku, jurnal penelitian sejenis meupun e-book yang dapan mendukung penulisan tugas akhir ini, yaitu yang menjelaskan tentang sistem pendukung kepuusan (spk) dengan menggunakan metode weighted product (wp). metode pengumpulan data, populasi, dan sampel penelitian a. metode pengumpulan data metode pengumpulan data yang dilakukan peneliti terbagi menjadi 2 (dua) cara, yaitu: dengan melakukan observasi langsung dan wawancara untuk mendapatkan data primer. data sekunder berasal dari mengumpulkan dan mengidentifikasi serta mengolah data tertulis berbentuk buku-buku dan jurnal yang berkaitan dengan penelitian. b. populasi dan sampel populasi populasi adalah wilayah generalisasi yang terdiri atas: obyek/subyek yang mempunyai kualitas dan karakteristik tertentu yang diterapkan oleh peneliti untuk mempelajari dan kemudian dutarik kesimpulannya.(sugiyono, 2017) sampel adalah bagian dari jumlah dan karakteristik yang dimiliki oleh populasi tersebut.(sugiyono, 2017) dalam penelitian ini, penulis melakuan observasi dan wawancara langsung dengan hrd di salah satu perusahaan pt. hi-lex indonesia di tangerang. populasi yang akan diambil pada salah satu divisi yang sedang memiliki 1 (satu) sampel calon karyawan yang akan diterima oleh perusahaan sebanyak 50 orang. dari populasi tersebut akan diambil 10 (sepuluh) sampel. metode analisis data analisa adalah bagian penting dalam metodologi penelitian ilmiah, dikarenakan dengan melakukan analisis data tersebut dapat diberi arti dan makna yang berguna dalam suatu penyelesaian masalah. metode weighted product (wp) merupakan metode pengambilan keputusan yang diperhitungkan secara kuantitatif (perhitungan matematika sesuai dengan rumus weighted product). langkah-langkah dalam perhitungan metode weighted product (wp) adalah sebagai berukut (sari, 2018): a. menentukun kriteria-kriteria yang akan dijadikan acuan dalam pengambilan keputusan b. menentukan rating kecocokan setia alternatif pada setiap kriteria c. menentukan bobot referensi setiap kriteria d. mengalihkan seluruh atribut bagi sebuah alternatif dengan bobot sebagai pangkat positif untuk atribut keuntungan dan bobot berpangkat negatif untuk atribut biaya e. hasil perkalian tersebut dijumlahkan untuk mengahasilkan nilai vektor v untuk setiap alternatif f. mencari nilai alternatif dengan melakukan langkah yang sama seperti pada langkah 1 (satu), hanya saja menggunakan nilai tertinggi untuk setiap atribut tertinggi untuk setiap atribut manfaat dan nilai terendah untuk atribut biaya g. membagi nilai v bagi setiap alternatif dengan nilai standar h. mencari nilai alternatif ideal yakni dengan merangking nilai vektor v sekaligus membuat kesimpulan sebagai tahap akhir preferensi untuk alternatif ai diberikan sebagai berikut (pratiwi, 2016): 𝑊𝑗 = 𝑤𝑗 ∑ 𝑊𝑗 (1) 𝑆𝑖 = ∏ = 𝑛 𝑗 1 𝑋𝑖𝑗 𝑤𝑗 (2) dimana : s = menyatakan preferensi alternatif dianalogikan sebagai vektor s x = menyatakan nilai kriteria w = menyatakan nilai bobot kriteria i = menyatakan alternatif j = menyatakan kriteria n = menyatakan banyaknya kriteria wj = menyatakan pangkat bernilai positif untuk atribut keuntungan, dan bernilai negative untuk atribut biaya. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 12 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional preferensi relatif dari setiap alternative, diberikan sebagai berikut: 𝑉𝑖 = π𝑗 𝑛=1 𝑋𝑖𝑗 𝑤𝑗 π𝑗 𝑛=1 (𝑋𝑗∗ ) 𝑤𝑗 (3) dimana : v = preferensi alternatif dianalogikan sebagai vektor v x = menyatakan nilai kriteria w = menyatakan bobot kriteria i = menyatakan alternatif j = menyatakan kriteria n = menyatakan banyaknya kriteria * = banyaknya kriteria yang telah dinilai pada vektor s hasil dan pembahasan perhitungan dengan metode weighted product (wp) perusahaan pt.hi-lex indonesia pada bulan april 2019 membuka lowongan untuk 1 (satu) orang. sebagai sampel perhitungan metode weighted product dalam seleksi penerimaan karyawan baru sebanyak 10 (sepuluh) pelamar yang akan diseleksi. menentukan bobot kriteria berikut menentukan bobot kriteria pada penerimaan karyawan baru pt. hi-lex indonesia, terdapat 7 (tujuh) kriteria yang akan ditentukan, antara lain: kriteria tes wawancara, kriteria tes psikotes, kriteria tes kesehatan, kriteria pengalaman kerja, kriteria pendidikan terakhir, kriteria usia, dan kriteria penampilan. tabel 1. data pelamar no nama tes wawancara tes psikotes tes kesehatan pengalaman kerja pendidikan terakhir usia penampilan 1 sarinah cukup sangat baik baik 2 tahun d3 22 tahun sangat baik 2 jilmah cukup buruk baik 2 tahun s1 21 tahun sangat baik 3 nuradiah baik buruk baik 1 tahun s1 21 tahun baik 4 iyan handoko baik sangat baik baik 0 tahun sma 22 tahun buruk 5 nurma cukup buruk baik 0 tahun sma 23 tahun buruk 6 sulaiman sangat baik sangat baik sangat baik 1 tahun d1 27 tahun sangat baik 7 rafli baik baik baik 0 tahun sma 22 tahun sangat buruk 8 nur isnaini baik cukup sangat baik 3 tahun s1 27 tahun sangat baik 9 aprilia assyifa m.n cukup baik baik 1 tahun d3 21 tahun sangat baik 10 sukirman sangat baik sangat baik sangat baik >3 tahun s1 28 tahun baik konversi nilai pelamar menentukan rating kecocokan setiap alternatif pada setiap kriteria. tabel 2. konversi nilai data pelamar no. alternatif nilai kriteria c1 c2 c3 c4 c5 c6 c7 1 a1 3 5 4 3 3 2 5 2 a2 3 2 4 3 4 2 5 3 a3 4 2 4 2 4 2 4 4 a4 4 5 4 1 1 2 2 5 a5 3 2 4 1 1 3 2 6 a6 5 5 5 2 2 5 5 7 a7 4 4 4 1 1 2 1 8 a8 4 3 5 4 4 5 5 9 a9 3 4 4 2 3 2 5 10 a10 5 5 5 5 4 5 4 ket: c1 : tes wawancara c2 : tes psikotes c3 : tes kesehatan c4 : pengalaman kerja c5 : pendidikan terakhir c6 : usia c7 : penampilan tingkat kepentingan penentuan bobot berdasarkan nilai tingkat kepentingan masing-masing kriteria, tingkat kepentingan setiap kriteria dinilai dengan 1 sampai 5. tingkat kepentingan dapat dilihat pada tabel. 3. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 13 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional tabel.3. tingkat kepentingan tingkat kepentingan nilai sangat rendah 1 rendah 2 cukup 3 baik 4 sangat baik 5 nilai bobot atau bobot awal (w) masingmasing kriteria telah ditentukan oleh pihak pt. hilex indonesia pada tabel 4 dibawah ini. tabel .4. pembobotan kriteria kode bobot c1 5 c2 5 c3 5 c4 4 c5 3 c6 3 c7 4 perbaikan bobot perkriteria setelah mendapatkan nilai bobot pada masing-masing kriteria, selanjutnya dilakukan perbaikan bobot dari nilai bobot awal. untuk mendapatkan hasil tersebut dengan menggunakan perhitungan sebagai berikut: a. hasil untuk perhitungan bobot pada kriteria tes wawancara dengan nilai 5 adalah 0,17 b. hasil untuk perhitungan bobot pada kriteria tes psikotes dengan nilai 5 adalah 0,17 c. hasil untuk perhitungan bobot pada kriteria tes kesehatan dengan nilai 5 adalah 0,17 d. hasil untuk perhitungan bobot pada kriteria pengalaman kerja dengan nilai 4 adalah 0,14 e. hasil untuk perhitungan bobot pada kriteria pendidikan terakhir dengan nilai 3 adalah 0,10 f. hasil untuk perhitungan bobot pada kriteria usia dengan nilai 3 adalah 0,10 g. hasil untuk perhitungan bobot pada kriteria penampilan dengan nilai 4 adalah 0,14 berikut merupakan ringkasan dari proses dari perhitungan hasil perbaikan bobot pada setiap kriteria pada tabel 5, dibawah ini. tabel 5. bobot preferensi bobot kriteria nilai (w) c1 0,17 c2 0,17 c3 0,17 c4 0,14 c5 0,10 c6 0,10 c7 0,14 perhitungan nilai vektor s setelah dilakukan perbaikan bobot, dilakukan perhitungan nilai vektor (s), dengan memangkatkan dan mengalikan nilai masingmasing kriteria tersebut dengan bobot yang sudah diperbaiki sebelumnya, dengan perhitungan sebagai berikut: a. hasil perhitungan dari masing-masing kriteria pada alternatif 1 adalah 3,5055 b. hasil perhitungan dari masing-masing kriteria pada alternatif 2 adalah 3,0874 c. hasil perhitungan dari masing-masing kriteria pada alternatif 3 adalah 2,9690 d. hasil perhitungan dari masing-masing kriteria pada alternatif 4 adalah 2,4876 e. hasil perhitungan dari masing-masing kriteria pada alternatif 5 adalah 2,1110 f. hasil perhitungan dari masing-masing kriteria pada alternatif 6 adalah 3,9489 g. hasil perhitungan dari masing-masing kriteria pada alternatif 7 adalah 2,1735 h. hasil perhitungan dari masing-masing kriteria pada alternatif 8 adalah 4,2094 i. hasil perhitungan dari masing-masing kriteria pada alternatif 9 adalah 3,1888 j. hasil perhitungan dari masing-masing kriteria pada alternatif 10 adalah 4,6636 pada tabel 6. merupakan penjelasan preferensi vektor s yaitu hasil nilai dari setiap alternatif serta jumlah total seluruh nilai vektor s. tabel 6. nilai preferensi vektor s preferensi alternatif nilai vektor s s1 3.5055 s2 3.0874 s3 2.9690 s4 2.4876 s5 2.1110 s6 3.9489 s7 2.1735 s8 4.2094 s9 3.1888 s10 4.6636 total 32.3447 menghitung preferensi (vi) untuk perangkingan menghitung preferensi prengkingan untuk mendapatkan nilai hasil dengan melakukan pembagian dengan rata-rata dari nilai setiap perkalian, dengan proses perhitungan sebagai berikut: a. hasil perhitungan vektor v pada alternatif 1 dengan nilai 3.5055 adalah 0,1084 b. hasil perhitungan vektor v pada alternatif 2 dengan nilai 3.0874 adalah 0,0955 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 14 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional c. hasil perhitungan vektor v pada alternatif 3 dengan nilai 2.9690 adalah 0,0917 d. hasil perhitungan vektor v pada alternatif 4 dengan nilai 2.4876 adalah 0,0769 e. hasil perhitungan vektor v pada alternatif 5 dengan nilai 2.1110 adalah 0,0653 f. hasil perhitungan vektor v pada alternatif 6 dengan nilai 3.9489 adalah 0,1221 g. hasil perhitungan vektor v pada alternatif 7 dengan nilai 2.1735 adalah 0,0672 h. hasil perhitungan vektor v pada alternatif 8 dengan nilai 4.2094 adalah 0,1302 i. hasil perhitungan vektor v pada alternatif 9 dengan nilai 3.1888 adalah 0,0986 j. hasil perhitungan vektor v pada alternatif 10 dengan nilai 4.6636 adalah 0,1442 pada tabel.7. merupakan ringkasan hasil nilai vektor v pada setiap alternatif yang telah terhitung diatas. tabel7. preferensi alternatif vektor v preferensi alternatif nilai vektor v v1 0,1084 v2 0,0955 v3 0,0917 v4 0,0769 v5 0,0653 v6 0,1221 v7 0,0672 v8 0,1302 v9 0,0986 v10 0,1442 proses perangkingan proses hasil prengkingan seleksi administrasi yang sudah dilakukan beberapa perhitungan diatas maka didapatkan hasil seperti tabel 8. dibawah ini: tabel 8, hasil perangkingan seleksi administrasi no alternatif nilai vektor v rangking 1 a1 0,1084 4 2 a2 0,0955 6 3 a3 0,0917 7 4 a4 0,0769 8 5 a5 0,0653 10 6 a6 0,1221 3 7 a7 0,0672 9 8 a8 0,1302 2 9 a9 0,0986 5 10 a10 0,1442 1 gambar .2. grafik hasil perangkingan hasil seleksi hasil seleksi calon karyawan baru diambil sebanyak 1 (satu) orang yang dibutuhkan oleh perusahaan pt. hi-lex indonesia, dimana data-data karyawan dihitung bobot penilaianya dijabarkan pada tabel .16. dibawah ini: tabel.16. hasil seleksi no alternatif nilai vektor v rangking 1 a10 0,1442 1 2 a8 0,1302 2 3 a6 0,1221 3 4 a1 0,1084 4 5 a9 0,0986 5 6 a2 0,0955 6 7 a3 0,0917 7 8 a4 0,0769 8 9 a7 0,0672 9 10 a5 0,0653 10 sesuai dengan hasil perhitungan menggunakan metode weighted product untuk penyeleksian karyawan baru terpaparkan pada tabel .16. diatas, selanjutnya didapatkan 1 (satu) alternatif calon karyawan baru terbaik yaitu a10 atas nama sukirman. simpulan dan saran kesimpulan berdasrkan maksud dan tujuan penelitian, pengolahan data dan analis yang telah dilakukan oleh penulis, maka dapat ditarik kesimpulan adalah sebagai berikut: pemilihan bobot penilaian dapat dikembangkan dengan kriteria-kriteria yang lain sesuai dengan kebutuhan perusahaan, dimana perusahaan dapat menyesuaikan dengan kondisi dan iklim perusahaan. berdasarkan beberapa http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 15 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional jurnal penelitian dengan pemilihan karyawan baru dengan menggunakan metode weighted product, bahwa metode tersebut lebih akurat mendapatkan hasil perhitungan bobot kriteria. hasil perhitungan dengan menggunakan metode weighted product, dengan acuan kriteria tes wawancara, tes psikotes, tes kesehatan, pengalaman kerja, pendidikan terakhir, usia dan penampilan, maka terpilih 1 (satu) orang calon karyawan, yang bernama sukirman yang akan menjadi karyawan di pt.hilex indonesia. saran-saran dari hasil penelitian yang dilakukan oleh penulis, maka dapat diusulkan beberapa saran untuk penelitian lanjutan sebagai berikut: studi penelitian dapat dilakukan juga pada perusahaan lainnya dan dapat dikembangkan dengan metode penelitian seperti topsis. penelitian dapat dikembangkan lebih lanjut dengan kriteria-kriteria yang berbeda sesuai dengan kriteria dan bobot yang ditentukan perusahaan tempat dilakukannya penelitian. semoga apa yang telah dihasilkan dalam penulisan ini dapat bermanfaat dan dapat membantu seorang atasan atau bagian hrd dalam pengambilan keputusan untuk menentukan calon karyawan yang akan diterima menjadi karyawan di pt. hi-lex indonesia. penulisan ini sangat jauh dari kata sempurna, oleh karena itu sangat diperlukan masukan, saran, dan kritik yang membangun dan dapat memperbaiki penelitian ini menjadi lebih baik. references agustin, y. h., & kurniawan, h. (2015). sistem pendukung keputusan penilaian kinerja dosen menggunakan metode weighted product (studi kasus : stmik pontianak) | agustin | seminar nasional informatika (snif). in seminar nasional informatika (pp. 177–182). lppm universitas potensi utama. retrieved from http://ejournal.potensiutama.ac.id/ojs/index.php/snif/article/view /261 amalia, r. m., & utami, d. y. (2018). pemberian reward berdasarkan penilaian kinerja karyawan dengan metode ahp pada pt. anugerah protecindo. jurnal ilmu pengetahuan dan teknologi komputer, 3(2), 181–188. ariani, f. (2017). sistem penunjang dalam penentuan prioritas pemilihan percetakan media promosi menggunakan metode ahp. jurnal informatika, 4(2). https://doi.org/10.31311/ji.v4i2.2122 fajarianto, o., iqbal, m., & cahya, j. t. (2017). sistem penunjang keputusan seleksi penerimaan karyawan dengan metode weighted product. jurnal sisfotek global, 7(1), 49–55. retrieved from http://journal.stmikglobal.ac.id/index.php/si sfotek/article/view/128 ismail, & nurjaya. (2016). seleksi penerimaan karyawan baru menggunakan metode wp (weighted produck) dengan bahasa pemrograman php dan mysql. jurnal informatika universitas pamulang, 1(1), 28– 32. retrieved from http://openjournal.unpam.ac.id/index.php/i nformatika/article/view/1465 mirawati, hikmah, a. b., & wiguna, w. (2018). sistem penunjang keputusan penilaian kinerja kasir lotte mart menggunakan metode weighted product. ijcit (indonesian journal on computer and information technology), 3(2), 186–196. moenir, a., & budiyanto, s. (2018). penerapan metode weighted product (wp) berbasis web untuk pemilihan ketua pada dewan kerja gerakan pramuka kwartir cabang kota tangerang. in seminar nasional informatika dan sistem informasi (pp. 84–96). tangerang selatan: universitas pamulang. retrieved from http://openjournal.unpam.ac.id/index.php/s nisis/article/view/3070 pratiwi, h. (2016). buku ajar sistem pendukung keputusan. yogyakarta: deepublisher. putra, c. i., & ferdiansyah, f. (2018). implementasi dan pembuatan sistem penunjang keputusan penerimaan karyawan di pt genesis indotama teknologi menggunakan metode weighted product berbasis web. skanika, 1(3), 987–994. retrieved from http://jom.fti.budiluhur.ac.id/index.php/ska nika/article/view/2500 rahmawati, a., & astuti, y. (2018). implementasi weighted product untuk penerimaan karyawan. jurnal mantik penusa, 2(1), 28–34. retrieved from http://ejurnal.pelitanusantara.ac.id/index.php/manti http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 16 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional k/article/view/321 sari, f. (2018). metode dalam pengambilan keputusan. (s. novidiantoko & h. a. susanto, eds.) (buku). yogyakarta: deepublish publisher. sugiyono. (2017). metode penelitian kuantitatif, kualitatif, dan r&d (buku). bandung: alfabeta. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 227 the work is distributed under the creative commons attribution-noncommercial 4.0 international license decision support system for selection of exemplary employees at pt. sinar asia perkasa syahriani, nurmah, luthfi indriyani informatics engineering, information systems, sekolah tinggi manajemen informatika dan komputer nusa mandiri www.nusamandiri.ac.id syahriani.yii@nusamandiri.ac.id, nurmahn15@gmail.com computer technology universitas bina sarana informatika www.bsi.ac.id luthfi.lfy@bsi.ac.id abstrak pt. sinar asia perkasa merupakan perusahaan manufaktur, dimana perusahaan ini selalu dituntut untuk melakukan inovasi dan meningkatkan mutu serta kualitas produknya. karena perihal tersebut, maka perusahaan pt. sinar asia perkasa harus berbenah diri agar mendapatkan karyawan yang memiliki kualitas dan produktivitas kerja yang tinggi. karyawan merupakan salah satu bagian terpenting dalam perusahaan yang harus dikelola secara baik. untuk mendapatkan karyawan dengan kualitas terbaik, dibutuhkan proses yang dapat secara langsung memberikan rekomendasi dalam memilih karyawan teladan pada pt. sinar asia perkasa yaitu dengan dibuatkannya sistem pendukung keputusan. sistem pendukung keputusan ini, diharapkan dapat membantu dalam pemilihan karyawan teladan dengan penilaian secara objektif. pembuatan sistem pendukung keputusan ini menggunakan metode profile matching dengan beberapa kriteria yaitu aspek disiplin, aspek integritas, aspek kerjasama, dan aspek prestasi kerja. kemudian untuk tahapan akhir dari metode ini adalah perankingan. kata kunci: profile matching, karyawan teladan, sistem penunjang keputusan abstract pt. sinar asia perkasa is a manufacturing company, where this company is always required to innovate and improve the quality and quality of its products. because of this, the company pt. sinar asia perkasa must improve itself to get employees who have high quality and work productivity. employees are one of the most important parts of a company that must be managed properly. to get employees of the highest quality, a process is needed that can automatically provide recommendations in selecting exemplary employees at pt. sinar asia perkasa, namely by establishing a decision support system. this decision support system is expected to assist in objectively selecting employees. making this decision support system using the profile matching method with several criteria, namely aspects of the discipline, aspects of integrity, aspects of cooperation, and aspects of work performance. then for the final stage of this method is ranking. keywords: profile matching, exemplary employees, decision support system introduction employees have an important role and are the spearhead for the development of a company or institution. a company that is successful in running its business cannot escape the hard work done by its employees. therefore, for the smooth running and development of a company, the quality and productivity of its employees need to be improved and maintained properly. pt. sinar asia perkasa has problems in selecting exemplary employees, where the company still uses a subjective one-way assessment(purwanto, 2017), (ricki & devitra, 2019) because it does not have a systematic method or indicator that is applied. pt. sinar asia perkasa needs to improve itself in the process of managing its human resources. if human resources can be well organized, it is hoped that the company can carry http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 228 the work is distributed under the creative commons attribution-noncommercial 4.0 international license out all its business processes properly(penta, siahaan, and sukmana, 2019). therefore the company pt. sinar perkasa requires a decision support system for selecting exemplary employees in its company. decision support systems are part of a computer-based information system including knowledge-based or knowledge management systems that are used to support decision making in an organization or company. (pareda, mongi, and montolalu, 2019). the method used in the decision support system process is the profile matching method. (sudrajat, 2018), (mashyur & frieyadie, 2019). the concept of the profile matching method is to compare individual competencies into job competencies so that differences incompetence can be found (called gap). (triandi, 2011), the smaller the resulting gap, the greater the weighted value, which means that there is a greater chance for someone to occupy that position (susilo, 2018). also, according to atmanagara et al, this method is very suitable for use in human resource management efforts, because in the process of the profile matching method in outline is a process of comparing individual abilities to competencies that must be achieved in a position (atmanagara, putri, and sutrisno, 2017). research on decision support systems for selecting exemplary employees at pt. sinar asia perkasa is made based on data and special criteria used to support employee quality and productivity. the gap calculation process is carried out to determine the points of each criterion and match the weighting of each criterion. then the results of the calculation process will produce employee rankings. research methods this study uses the profile matching method. according to merlina and hidayat, the stages and processes of searching for ranking values using the profile matching method are as follows (merlina and hidayat, 2012): 1. weighted value the weight value is used to find the gap value or the difference between the value of the employee profile and the value of the best employee profile, which can be written with the formula: 𝐺𝐴𝑃 = 𝑁𝑖𝑙𝑎𝑖 𝐾𝑎𝑟𝑦𝑎𝑤𝑎𝑛 – 𝑁𝑖𝑙𝑎𝑖 𝑆𝑡𝑎𝑛𝑑𝑎𝑟 (𝑀𝑖𝑛𝑖𝑚𝑢𝑚) ......... (1) 2. calculation and grouping of core and secondary factors after determining the weight of the gap value, the next step is to calculate and group the values based on the core factor and secondary factor. a. core factor value calculation the calculation of the core factor value is shown in the formula below: 𝑁𝑅𝐶 = 𝛴𝑁𝐶 𝛴𝐼𝐶 ...................................................................... (2) information: nrc: average value core factor nc: the total number of the scores core factor ic: amount of core factor items b. calculation of secondary factor value the calculation of the second-factor value is shown by the formula below: 𝑁𝑅𝐶 = 𝛴𝑁𝐶 𝛴𝐼𝑆 ...................................................................... (3) information: nrf: average value secondary factor ns: the total number of scores secondary factor is: amount of secondary factor item 3. total value calculation from the results of the weighted value calculation and the grouping of core factor and secondary factor, then the total value is calculated based on the percentage of cores and secondary factors that are estimated to affect the performance of each profile. the formula is as follows: 𝑁𝑇 = [𝑥]%𝑁𝐶𝐹 + [𝑥]% 𝑋 𝑁𝑆𝐹 ................................... (4) information: nt: the total value of the variable (x)%: the percent value entered ncf: average value core factor nsf: average value secondary factor 4. ranking determination calculations the final result of the profile matching process is ranking. ranking refers to the results of certain calculations, which are shown in the formula below: 𝑅𝑎𝑛𝑔𝑘𝑖𝑛𝑔 = [𝑥]% 𝑋 𝑁1 + [𝑥]% 𝑋 𝑁2 + [𝑥]%𝑋 𝑁3 + [𝑥]% 𝑋 𝑁4 ................................................... (5) source: (adhar, 2014) information: n1, n2, n3, n4: the total calculated aspect value (x)% : the percent value entered likert scale the likert scale is a scale used to measure the attitudes, opinions, and perceptions of a person http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 229 the work is distributed under the creative commons attribution-noncommercial 4.0 international license or group of people regarding a symptom or phenomenon that will be used as a benchmark or to test how strong a statement consisting of 5 points, in table 1 including (sugiyono, 2016) table 1. likert scale no. information score 1 very agree / always / very positive 5 2 agree / often / positive 4 3 indecisive / occasional / neutral 3 4 disagree / almost never / negatively 2 5 strongly disagree / never 1 research procedure the procedures or stages of this research are: figure 1. procedure or research stages data collection technique the research methods used by the authors in conducting this research are: a. observation the data and information obtained related to the selection process for the best employees is direct research at pt. sinar asia perkasa, penjaringan, north jakarta. b. interview this study conducted interviews with resource persons, namely mr. stevanus vincent susanto, se, as the hrd manager at the company. c. literature review the author is looking for various references such as books, online journals, previous works, ebooks, literature studies, and others related to the theme the author takes. d. questionnaire the questionnaire is designed in the form of a likert scale based on the profile matching method, namely, there are 5 sub-criteria response values. value 5 for a very good response, score 4 for a good response, score 3 for an adequate response, score 2 for poor response, and value 1 for very poor response. data analysis technique sampling technique the sample was determined by a population at pt. sinar asia perkasa uses the quota sampling technique, which is part of the nonprobability sampling which consists of the information technology, finance & accounting, promotion, shipping and security sections, along with the data (taken for example the it department) in table 2. table 2. sample it department employees no. name position 1. ahmad suhelji it hardware 2. galant fadhila it design 3. andi sulasikin it design 4. hifsar septiyawan creative design 5. muhammad albanjaari digital account executive 6. nadya alwin digital account executive criteria and sub criteria the criteria and sub-criteria are determined in table 3 as follows. table 3. criteria and sub criteria no. criteria sub criteria 1. discipline aspects responsible be on time appearance polite manners 2. aspects of integrity professional consistent 3. cooperation aspects group work participate & contribute active & productive helping colleagues 4. aspects of work performance complete tasks above standard complete tasks based on standards perform performance improvements research results and discussion classification of core factor and secondary factor after determining the gap from each predetermined aspect, namely the aspect of discipline, aspects of integrity, aspects of cooperation, and aspects of work performance, then next is to determine the core factor and http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 230 the work is distributed under the creative commons attribution-noncommercial 4.0 international license secondary factor of each of these sub-criteria can be seen in table 6. a. core factor (main aspect), is the most favored aspect and has a high value to get the maximum results from this best employee data management. b. secondary factor (supporting aspects), is an aspect that supports the main aspects. table 4. core factor and secondary factor no. aspect core secondary 1. discipline a. responsible b. be on time c. appearance d. politeness 2. integrity a. professional b. consistent 3. cooperation a. group work b. participate & contribute c. active & productive d. helping colleagues 4. work performance a. complete tasks above standard b. complete tasks based on standards c. perform performance improvements information on the value of the aspect sub criteria then it can be seen for the sub-criteria aspect values in table 5 below: table 5. value of sub criteria aspects sub criteria value 1 = less 2 = enough 3 = good 4 = satisfactory 5 = very satisfying gap value calculation table 6 is the calculation result from the aspect of discipline for the information technology section. table 6. discipline aspects of gap value weighting results in part ti no name disciplinary aspects ket d1 d2 d3 d4 1 ahmad suhelji 3 1 2 2 2 galant fadhila 2 1 2 3 3 andi sulasikin 2 2 3 4 4 hifsar septiyawan 3.5 3 3 3 5 muhammad albanjaari 2 2 3 5 6 nadya alwin 3 3 3 4 standard value 5 5 4 4 1 ahmad suhelji -2 -4 -2 -2 gap 2 galant fadhila -3 -4 -2 -1 3 andi sulasikin -3 -3 -1 0 4 hifsar septiyawan -1.5 -2 -1 -1 5 muhammad albanjaari -3 -3 -1 1 6 nadya alwin -2 -2 -1 0 convert value to weight 1 ahmad suhelji 3 1 3 3 gap 2 galant fadhila 3.5 1 3 4 3 andi sulasikin 2 2 4 5 4 hifsar septiyawan 4 3 4 4 5 muhammad albanjaari 2 2 4 4.5 6 nadya alwin 3 3 4 5 calculation and grouping ncf and nsf table 7 below is the calculation and grouping of ncf and nsf from disciplinary aspects in the field of ti: table 7. core dan secondary factor of discipline aspects in part ti name disciplinary aspects cf sf d1 d2 d3 d4 ncf=(d1+d2)/2 nsf=(d3+d4)/2 ahmad suhelji 3 1 3 3 2 3 galant fadhila 3.5 1 3 4 2.25 3.5 andi sulasikin 2 2 4 5 2 4.5 hifsar septiyawan 4 3 4 4 3.5 4 muhammad albanjaari 2 2 4 4.5 2 4.25 nadya alwin 3 3 4 5 3 4.5 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 231 the work is distributed under the creative commons attribution-noncommercial 4.0 international license calculation of total value table 8 is a calculation of the total value of the disciplinary aspects of the ti: table 8. total value of disciplinary aspects section ti name cf sf result % n1 ncf (60%) nsf(40%) nt = 60%ncf+ 40%nsf ahmad suhelji 2 3 1.2 1.2 2.4 galant fadhila 2.25 3.5 1.5 1.4 2.9 andi sulasikin 2 4.5 1.2 1.8 3 hifsar septiyawan 3.5 4 2.1 1.6 3.7 muhammad albanjaari 2 4.25 1.2 1.7 2.9 nadya alwin 3 4.5 1.8 1.8 3.6 ranking calculation for the determination of ranking results obtained from the formula: ranking = (25% x discipline) + (20% x integrity) + (25% x cooperation) + (30% x job performance) table 9. final results of ranking section ti name n1 n2 n3 n4 n1 n2 n3 n4 final result 25% 20% 25% 30% ahmad suhelji 2.4 3.8 4.22 3.4 0.6 0.76 1.055 1.02 3.47 galant fadhila 2.9 4.4 4.4 4.4 0.725 0.88 1.1 1.32 3.91 andi sulasikin 3 4.4 4.4 4.4 0.75 0.88 1.1 1.32 4.05 hifsar septiyawan 3.7 5 4.58 4.4 0.925 1 1.145 1.32 4.39 muhammad albanjaari 2.9 4.4 4.4 4.4 0.725 0.88 1.1 1.32 4.03 nadya alwin 3.6 4.4 4.4 4.4 0.9 0.88 1.1 1.32 4.20 table 10. section ranking results in ti name the final result ranking hifsar septiyawan 4.39 1 nadya alwin 4.2 2 andi sulasikin 4.05 3 muhammad albanjaari 4.03 4 galant fadhila 4.03 5 ahmad suhelji 3.44 6 from table 10 can already be seen the final result to select exemplary employees in the field of it, where the first rank is occupied by hifsar septiyawan, the second level is occupied by nadya alwin, the third place occupied by andi sulasikin, the fourth-place occupied by muhammad albanjaari, the fifth-place occupied by galant fadhila and the last rank occupied by ahmad suhelji. conclusions and recommendations conclusion based on the research that has been carried out, it can be concluded that to determine the capacity of employees using profile matching method can be used the results of individual values converted to weight values i.e. by comparing between individual competencies into the competencies of the best employees so that it can be known the difference in competencies (called gaps) which if the resulting gap is smaller then the opportunity to become the best employee is more wide open. researchers create a decision support system as a tool in making decisions by collecting data, conducting interviews with the parties concerned, analyzing from the data generated by profile matching method, gap calculation, core and secondary factor grouping, calculation of yield value to stamping in the place used as a research site namely pt. sinar asia perkasa. addressing the assessment conducted subjectively is by determining several criteria for the assessment using the profile matching method by giving questionnaires to the boss of each division and the questionnaire results will be calculated so that the questionnaire results can produce accurate data. recommendation from the results of research conducted on the decision support system (spk) of the best employees in pt. sinar asia perkasa, then researchers proposed several suggestions including developing the system by adding methods such as simple additive weighting, analytical hierarchy process, or others so that results may be more accurate. implement this method by building a web or desktop-based http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 232 the work is distributed under the creative commons attribution-noncommercial 4.0 international license decision support system so that decision-makers find it easier and the system more efficient reference adhar, d. (2014). sistem pendukung keputusan pengangkatan jabatan karyawan pada pt . ayn dengan metode profile matching. jurnal teknik informatika dan sistem informasi, 1(1), 16–29. atmanagara, f. d. s., putri, r. r. m., & sutrisno, s. (2017). implementasi metode profile matching untuk seleksi penerimaan anggota asisten praktikum ( studi kasus : laboratorium pembelajaran kelompok praktikum basis data filkom ). jurnal pengembangan teknologi informasi dan ilmu komputer (j-ptiik) universitas brawijaya, 1(12), 1804–1812. retrieved from http://j-ptiik.ub.ac.id/index.php/jptiik/article/view/663 mashyur, r. s., & frieyadie, f. (2019). penggunaan metode profile matching untuk pemilihan eosh captain terbaik pada pt.coca-cola indonesia. jurnal pilar nusa mandiri, 15(2), 235–240. https://doi.org/10.33480/pilar.v15i2.767 pareda, s., mongi, c. e., & montolalu, c. e. j. c. (2019). sistem pendukung keputusan pemilihan karyawan teladan di pt aneka tambang ( antam ) tbk unit bisnis pertambangan buli menggunakan metode simple additive weight ( saw ). d’cartesian: jurnal matematika dan aplikasi, 8(1), 1–10. retrieved from https://ejournal.unsrat.ac.id/index.php/deca rtesian/article/view/22676 penta, m. f., siahaan, f. b., & sukamana, s. h. (2019). sistem pendukung keputusan pemilihan karyawan terbaik menggunakan metode saw pada pt. kujang sakti anugrah. jsai (journal scientific and applied informatics), 2(3), 185–192. https://doi.org/10.36085/jsai.v2i3.410 purwanto, h. (2017). penerapan metode profile matching dalam sistem pendukung keputusan penilaian kinerja karyawan pada pt. hyundai mobil indonesia cabang kalimalang. jurnal techno nusa mandiri, 14(1), 15–20. ricki, r., & devitra, j. (2019). analisis dan perancangan sistem pendukung keputusan pemilihan karyawan terbaik pada pt. wahyu perdana persada dengan metode simple additive weighting (saw). jurnal manajemen sistem informasi, 4(3), 255–265. https://doi.org/10.33998/jurnalmanajem ensisteminformasi.2019.4.3.658 sudrajat, b. (2018). pemilihan pegawai berprestasi dengan menggunakan metode profile matching. journal of information system, applied, management, accounting and research, 2(4), 20–28. retrieved from http://polgan.ac.id/jurnal/index.php/sinkro n/article/177/ sugiyono. (2016). metode penelitian kuantitatif kualitataif dan kombinasi (mixed methods). alfabeta. susilo, a. a. t. (2018). penerapan metode profile matching pada sistem pendukung keputusan pemilihan ketua program studi (studi kasus : program studi teknik informatika stmik musi rawas). juita : jurnal informatika, 5(2), 87–93. https://doi.org/10.30595/juita.v5i2.1939 triandi, b. (2011). sistem pendukung keputusan untuk kenaikan jabatan menggunakan metode profile matching modeling. jurnal digit, 1(2), 143–152. retrieved from https://jurnaldigit.org/index.php/digit/arti cle/view/6 http://creativecommons.org/licenses/by-nc/4.0/ 233 employee turnover classification using pso-based naïve bayes and naïve bayes algorithm in pt. mastersystem infotama endang sri palupi sistem informasi universitas bina sarana informatika www.bsi.ac.id endang.epl@bsi.ac.id abstrak turnover yang terjadi karena banyak karyawan yang keluar dan karyawan yang baru masuk, sehingga perputaran keluar masuk karyawan cukup tinggi, karena itu turnover dapat dikendalikan dengan strategi peningkatan engagement karyawan. pt. mastersystem infotama adalah sebuah perusahaan system integrator atau lebih dikenal dengan perusahaan it yang cukup besar dengan jumlah karyawan keseluruhan kurang lebih 600 karyawan. turnover yang cukup tinggi membuat beberapa divisi kekurangan sumber daya manusia, dan divisi human capital management cukup kesulitan melakukan perekrutan karyawan untuk mencari kandidat dengan berbagai kriteria yang harus tersedia dalam waktu singkat. persaingan dunia it cukup ketat baik dalam perusahaan ataupun karyawan dengan pengalaman dan kemampuan yang sudah bagus. terutama bagian sales yang memegang database para customer yang potensial, dan bagian engineer yang sudah mempunyai sertifikat keahlian yang banyak digunakan dalam dunia bisnis it. oleh karena itu perlu diklasifikasi faktor apa saja yang membuat tingginya turnover karyawan dengan menggunakan algoritma naïve bayes dan naïve bayes berbasis particle swarm optimization, sehingga bisa menjadi bahan evaluasi internal untuk meningkatkan engagement karyawan. hasil penelitian ini klasifikasi menggunakan algoritma naïve bayes akurasinya sebesar 79.17% sedangkan klasifikasi menggunakan algoritma naïve bayes berbasis particle swarm optimization sebesar 94.17%. kata kunci: algoritma naïve bayes, particle swarm optimization, turnover abstract turnover occurs because many employees leave and new employees enter, so the turnover in and out of employees is quite high, therefore turnover can be controlled with a strategy to increase employee engagement. pt. mastersystem infotama is a system integrator company or better known as a fairly large it company with a total of approximately 600 employees. turnover is high enough to make some divisions lack human resources, and the human capital management division is quite difficult to recruit employees to find candidates with various criteria that must be available in a short time. competition in the it world is quite tight both within companies and employees with good experience and abilities. especially the sales department that holds a database of potential customers, and the engineer section that already has a certificate of expertise that is widely used in the it business world. therefore, it is necessary to classify what factors make employee turnover high by using the naïve bayes and naïve bayes algorithms based on particle swarm optimization, so that they can be used as material for internal evaluation to increase employee engagement. the results of this study, classification using the naïve bayes algorithm, has an accuracy of 79.17%, while the classification using the naïve bayes algorithm based on particle swarm optimization is 94.17%. keywords: algoritma naïve bayes, particle swarm optimization, turnover introduction the employee turnover rate in a company which is measured based on the number of workers in a certain period or known as high turnover is a serious problem at pt mastersystem infotama. with the increase in turnover, many projects are delayed or the team dismantles so that the project is not http://creativecommons.org/licenses/by-nc/4.0/ 234 completed on time. recruiting new employees is timeconsuming and costly, has to be by the specifications of the requirements, skills according to the positions required, not to mention the adaptation of employees to the current work system. for this reason, the company wants to minimize the turnover that occurs by improving several matters related to career development, company regulations, bonuses and incentives, the applicable system, and other policies. it is expected that after that the turnover rate at the company will decrease so that it can achieve the company's goals and targets well, and be able to compete with competing companies. (noviyanto, 2018) in previous research written by stefani arika noviyanti in a thesis entitled employee turnover prediction using the naïve bayes classification method in 2018, to predict employees who will resign in 2019. the results of this study are used for the development of employee planning so that they can assist in achieving the target company. meanwhile, the authors classify the turnover factors that occur, so that they can make better human resource development plans and increase employee engagement to reduce turnover. (noviyanto, 2018) in 2018 there was also research and was stated in a journal entitled classification of employee status determination using the naïve bayes method written by fattya ariani and friends. this study uses five attributes, namely: attendance, attitude, psychological test, interview, and appointment. the attributes used as labels are lifted. the result is that manual calculation and the use of rapidminer yield the same values. the value of c1 (lifted) is 0.567, while the value of c2 (not lifted) is 0.433. and the highest value is elevated. the difference with this study is that the authors classify the turnover factor, although many employees are appointed as permanent employees if the high turnover rate is futile and they have to recruit new employees again so that it takes time and operational costs. (ariani et al., 2018) another research was conducted by taufik asra in 2019 with the title comparison of c4.5, k-nn, and naïve bayes algorithms in employee admission using pso at pt. xyz. this study calculates employee acceptance in the company by comparing 3 algorithms, namely c4., k-nn, and naïve bayes. the result is the highest level of accuracy in the calculation with the naïve bayes algorithm optimized with pso with an accuracy rate of 91.25%. the difference with the author's research is that the author uses the naïve bayes algorithm and the pso-based naïve bayes algorithm and the authors classify the turnover factors that occur in the company. (asra, 2019) another journal that discusses classification using the naïve bayes algorithm in 2015 by alfa saleh with the title implementation of the naïve bayes classification method in predicting the amount of household electricity usage. this study uses 60 data on electricity users and the results are accurate with a percentage of 78.333% of the 60 data on electricity users, 47 electricity users have been classified correctly. the author uses more employee data, namely 400 permanent employee data so that more data can be classified. (saleh, 2015) the journal entitled decision support system for determining employee monthly incentives using the naïve bayes method was written by victor marudut mulia siregar in 2018. this study aims to determine the number of employee incentives and implemented them in a microsoft visual studio 2013 application. the results of the calculation use the naïve algorithm method. bayes is accurate and can be used to calculate appropriate incentives for each employee. the difference with this study is that the authors classify employee turnover using the naïve bayes algorithm method. (marudut et al., 2018) then in the journal written by taufik asra in 2019 entitled comparison of c4.5, k-nn and naïve bayes algorithms in employee admission using pso at pt. xyz, the result has the highest accuracy using the naïve bayes algorithm, optimized with pso, which is 91.25%. the difference with this journal is that the authors classify employee turnover while in this study the comparison of employee acceptance and the author only uses the naïve bayes algorithm and psobased naïve bayes algorithm. (asra, 2019) the journal with the title decision making for non-permanent employees to become permanent employees with a decision tree was written by febryantahauji and friends in 2018. this journal uses the c4.5 decision tree algorithm for the selection of permanent employee admissions. this study only uses the decision tree c4.5 algorithm method, there is no comparison. the purpose of this research is to avoid naughty people in the appointment of permanent employees so that the company gets qualified employees, while this study aims to classify employee turnover so that the company can create programs to increase employee engagement. (sembiring, 2018) the journal entitled prediction of employee promotion with the c4.5 algorithm (case study: senayan jakarta apartments) was written by sunarti in 2019. the results of the study were 78% accurate using the c4.5 algorithm. this journal only uses the c4.5 algorithm method and its purpose is to predict employee promotions. meanwhile, the authors compared the naïve bayes algorithm with the psobased naïve bayes algorithm to classify employee turnover. (sunarti, 2019) http://creativecommons.org/licenses/by-nc/4.0/ 235 furthermore, the journal entitled prediction of loyalty in employee engagement with the company using the c4.5 algorithm (case study of pt. xyz) was written by bayu ferdiansyah and leonard goeirmanto in 2020. the study conducted a loyalty survey using ees (employee engagement survey) with the google form application, for the question using excel. using the c4.5 algorithm to predict employee engagement loyalty using 1002 sample data. the result of accuracy is 90.11% with the statement that employees are not loyal to the company. this research uses only one algorithm, c4.5, with no comparison with other algorithms and does not use pso optimization. (bayu ferdiansyah, 2020) the next journal entitled application of employee status classification using the naïve bayes algorithm method at h. syaiful anwar hospital was written by rino guphita in 2018. this research is to classify the status of new employees using variables of education level, work experience, and basic salary. this study only uses one naïve bayes algorithm method and does not use pso optimization. this research is also implemented using php and mysql platforms. (rino gupitha, 2018) the research entitled factors affecting turnover intention of employees at pt. mandiri tunas finance bengkulu was written by andriyani prawitasari in 2005. the results of this study the factors that influence turnover are: age, length of work, education, attachment to the company, job satisfaction with the company, corporate culture. the author uses these factors as data attributes. the difference is that the authors calculate the accuracy of these factors. (prawitasari, 2016) the next journal reference is the journal entitled comparison of employee acceptance analysis using the c4.5 algorithm, k-nn, and psobased naïve bayes. this research was written by ayuni asistyasari and yosep nuryaman in 2019 by comparing the 3 algorithms used according to the journal title. the result of the lowest order accuracy is the classification using the c4.5 algorithm based on pso 86.25%, then the second classification uses the pso-based k-nn algorithm the accuracy value is 82.50%, and the last one with the highest accuracy is the classification using the naïve bayes algorithm. based on pso with an accuracy value of 91.25%. classification using the pso-based naïve bayes algorithm produces high scores as well as this study. (asistyasari, 2019) the journal entitled determination of work schedule based on employee data classification using the c4.5 decision tree method (case study of the university of muhammadiyah surabaya) was written in 2016 by triuli novianti and iwan santosa. this journal discusses determining employee work schedules based on classification using the c4.5 decision tree algorithm. the final result of all data using cross-validation 5 fold the accuracy is 70%. the journal only uses one algorithm, namely the decision tree algorithm c4.5 without using pso optimization so that there is no comparison of the results with other algorithms. (triuli novianti, 2016) the next journal entitled determination of overtime schedule with classification of employee data using the c4.5 algorithm was written by ikhsan romli and ahmad turmudi zy pda in 2020. this research was made to determine employee overtime schedules and the results were 91% accuracy with 86.05% precision and 92 recall. 5%. this study only uses one c4.5 algorithm without using pso optimization, while the authors use pso optimization for comparisons. (ikhsan romli, 2020) the next reference is the journal entitled naïve bayes algorithm analysis for classification of exemplary employees at pt. toyoseal indonesia, written by chandra naya and muhlisin in 2019. this study determines exemplary and non-exemplary employees (performance) in a company with 5 attributes, 160 data, and with only one algorithm method, namely naïve bayes with an accuracy of 81.25%, precision 77.78% and recall 87.50%. this research does not use optimization so there is no comparison to compare the results of its accuracy. (chandra naya, 2019) in 2019 deni anugrah sahputra and friends wrote a journal entitled determining the eligibility factors for employee admission using the decision tree algorithm at pt. outsourcing personnel. with the amount of data as many as 19163 candidates who applied in 2019, using the decision tree algorithm resulted in an accuracy of 73.27% and an auc value of 0.789. the most influential recruitment eligibility factors are references from friends, age from 26-30 years old, female gender, for office services positions, domiciled in jabodetabek, and undergraduate education level. this study only uses one algorithm, namely the decision tree, so there is no comparison for comparisons and does not use pso optimization. (sahputra & saelan, 2020) the purpose of this study is to classify the turnover factor at pt. mastersystem infotama so that the human capital management section can change the system or work program so that it can reduce the turnover rate at the company. with the decrease in the turnover rate, the employee's commitment to the company increases, saves time and costs for the recruitment of new employees, and employees last a long time to work at the pt mastersystem infotama company, so that all employees can more easily work together with the company to achieve targets and goals. http://creativecommons.org/licenses/by-nc/4.0/ 236 research methods this study uses the crisp-dm (crossindustry standard process for data mining) model. the cross-industry standard process for data mining (crisp-dm) was developed in 1996 by analysts from several industries. crisp-dm provides a standard data mining process for solving general problems of business or research units. (daniel t. larose, 2005) crisp-dm stands for cross-industry standard process model for data mining, which describes the data mining process in 6 stages. figure 1. stages of crisp-dm (larose, 2014) 1. business understanding base on figure 1. stages of crips-dm, the purpose of this study is to classify the turnover factors that occur in the company. it is hoped that the company can make a better work program and a more conducive office atmosphere, increase employee engagement with the company, and make employees feel more comfortable so that the turnover rate decreases. reduced turnover can reduce the budget for recruiting employees, running projects are not interrupted due to changes or lack of resources, sales last a long time so that good relationship with customers are well maintained because they are maintained with the same people. 2. data understanding at this stage, the authors take the employee data from the hcm section plus the results of the employee satisfaction survey at the company via a google form. data of 400 employees and only taken from employee data with permanent employee status, employees with contract status, and data from outsourcing is not taken. 3. data preparation after all, data has been collected there are several useless attributes that must be removed using remove useless attributes, after the remove useless attributes process in the rapid miner studio framework, the attributes used in the data are: name, age, years of service, education, the value of satisfaction with the company, loyalty, kpi and survive or not. 4. modelling in this phase, the authors conducted modeling using the rapid miner studio framework with the naïve bayes algorithm and the pso-based naïve bayes algorithm. first, the author uses the validation function and the naïve bayes algorithm to get the accuracy and auc values. then the two authors used the validation function and the pso-based naïve bayes algorithm to get the accuracy value and auc as a comparison. 5. evaluation at this stage, the authors evaluate the results of the modeling phase and the results using the psobased validation function and naïve bayes algorithm to get the accuracy value and the auc results are better using pso optimization. 6. deployment the best result of modeling is to use the naïve bayes algorithm based on particle swarm optimization with an accuracy value of 81.32% and an auc value of 0.837. the use of pso increases the classification accuracy value for weighting the naïve bayes algorithm. types of research this research uses qualitative methods with case studies at pt. mastersystem infotama is a system integrator company in jakarta. against the background of the high turnover rate at the company, which could hinder the company from achieving its target. time and place of research this research was conducted in february 2019 at pt mastersystem infotama in central jakarta. the author is an employee of the company, making it easier for permission and access to conduct observations and research to obtain data. research target / subject the subjects of this study were employees at pt. mastersystem infotama, to classify what factors cause high turnover rates. researchers conducted http://creativecommons.org/licenses/by-nc/4.0/ 237 observations, research, and interviews between office hours and during breaks. procedure this framework represents the steps and procedures that will be carried out in this research process. the research framework can be described in the following figure: figure 2. research framework (ryfa, 2020) 1. identification of problems by figure 2. the research framework in the identification of the problem, the problem is determining the turnover factor classification pattern so that the turnover rate decreases to achieve the company's target well. 2. data collection at the data collection stage in figure 2. research framework, the data used are the results of observations, research, interviews, and from the company what is the turnover rate that occurred in 2018. 3. manual data processing using the naïve bayes method the next step is shown in figure 2 of the research framework, which is processing data using the naïve bayes method. this step performs manual calculations using the naïve bayes formula from the data that has been obtained. 4. data processing using rapid miner then next is the use of the rapid miner application using the naïve bayes algorithm operation according to the steps in figure 2 of the research framework. 5. conclusion the last stage in the research framework stage is a conclusion. the conclusion is obtained after getting the results from both manual data processing and also using rapid miner. (ariani et al., 2018) data, instruments, and data collection techniques the author obtained data from the company's human capital management division in the form of 400 employee data. then the authors also conducted literature studies, observations, and interviews. 1. literature study collect literature, data, good information from scientific journals, books, websites, and magazines. 2. observation read and observe directly at the company where you research how the work system is happening every day so far. 3. interview interview with employee correspondents who work at the research company, what obstacles are often faced, what factors cause employees to want to resign, as well as confirm the results of the data obtained from observations. (ryfa, 2020) data analysis technique quantitative research, in general, can be described as scientific research that is used to test a theory, using a theory consisting of variables and models, analyzed and measured by statistical numbers. in this study, the authors used quantitative data analysis techniques, namely observation and interviews with employees to find out why the turnover rate was high, what factors caused turnover. the author also obtained employee data as many as 400 permanent employee data. it is hoped that with this research the human capital management division can implement and implement policies that can reduce employee turnover so that all employees and the company can work together to achieve goals and targets. results and discussion model testing with the naïve bayes algorithm using employee data with permanent employee status in 2018 as many as 400 employee data. http://creativecommons.org/licenses/by-nc/4.0/ 238 information gain feature selection process figure 3. remove useless attributes after the dataset is available, the next step is to remove unused attributes using the remove useless attributes operator in the rapidminer studio framework. as in figure 3 using the useless attributes function in the rapidminer studio framework. figure 4. information gain furthermore, in figure 4. the information gain, the authors weighting using the information gain operator on the framework rapidminer studio. table 1. employee data name age years of services (year) education value of satisfaction to the company loyalty kpi stay edi bakhtiar 57 14 diploma good good good yes endang sri palupi 38 7 magister good good good yes yanto susanto 55 14 high school good average average no alex yusuf efendy 40 14 magister average good not good no shanti cecilia 42 14 diploma good average good yes nadia rahmawati 35 14 diploma not good good average no cecilia fang 39 14 bachelor average good not good no kevin aryanti 32 14 diploma good good good yes ari baharudin 35 14 bachelor good good average yes aryo nugrohon 30 13 bachelor not good average not good no budi susanto 29 14 bachelor not good good average no paulus alexander 26 13 bachelor good average average no anita nurhasanah 23 14 high school good average good yes siti azarah 22 13 high school good good good yes muhammad dzikra 27 14 bachelor not good good average no ryan nurwahid 24 13 diploma average not good average no putra muhammad hadi 24 13 bachelor average not good average no rachmat setiawan 29 13 high school good good good yes wawan cahyadi 32 13 magister good good good yes fika taulani sari 24 13 bachelor good average good yes alfin dwi iswinantyo 23 12 bachelor good not good average no susi yulianti 22 12 high school good average not good no felicia cecilia que 27 12 bachelor not good good not good no after the process of removing unused attributes with the operator, removing useless attributes, and weighting them with the information gain operator, this is the employee data that is ready for use in table 1. employee data, naïve bayes classification in figure 5. design of the naïve bayes algorithm model, creating a model design using the naïve bayes algorithm using the rapid miner studio framework. figure 5. design of the naïve bayes algorithm model figure 6. validation of the naïve bayes algorithm figure 6. validation of the naïve bayes algorithm is a validation modeling using the naïve bayes algorithm using the rapid miner studio framework. figure 7. accuracy of the naïve bayes algorithm method http://creativecommons.org/licenses/by-nc/4.0/ 239 figure 7. accuracy of the naïve bayes algorithm method is modeling using the naïve bayes algorithm using the rapid miner studio framework figure 8. area under roc curve base on the figure 8 area under the roc curve, the auc value of 0.917 is a good classification category. naïve bayes classification then we will create a model design using the pso-based naïve bayes algorithm using the rapid miner studio framework. figure 9. design of the naïve bayes algorithm model based on particle swarm optimization figure 9 is the naïve bayes algorithm modeling design that is optimized using particle swarm optimization in the rapid miner studio framework. figure 10. particle swarm optimization process figure 10 is the process of using particle swarm optimization in the rapidminer studio framework. figure 11. validation of the naïve bayes algorithm based on particle swarm optimization figure 11 is the validation process of the naïve bayes algorithm based on particle swarm optimization using the rapid miner studio framework. figure 12. accuracy of the naïve bayes algorithm method based on particle swarm optimization base on figure 12 the results of the accuracy using the naïve bayes algorithm method based on particle swarm optimization amounted to 94.17%. figure 13. area under roc curve the auc value of 0.960 is a good classification category. http://creativecommons.org/licenses/by-nc/4.0/ 240 conclusions and suggestions conclusion the results of the classification of the naïve bayes algorithm have an accuracy of 79.17%, 66.67% precision, 91.30% recall, and auc 0.917. while the classification uses the naïve bayes algorithm method based on particle swarm optimization with an accuracy of 94.17.32%, 89.80% precision, 95.65% recall, and 0.960 auc. from the results, it can be seen that the pso-based naïve bayes algorithm method has better accuracy than using the naïve bayes algorithm method alone. suggestion for further research, you can use bigger attributes and more data. can use other algorithms that are optimized with particle swarm optimization so that the accuracy value is more perfect. references ariani, f., amir, alam, n., & rizal, k. (2018). klasifikasi penetapan status karyawan dengan menggunakan metode naive bayes. jurnal paradigma, xx(2), 33–38. https://doi.org/10.31294/p.v asistyasari, a. n. y. (2019). komparasi analisis penerimaan karyawan menggunakan. november, 519–525. https://doi.org/10.30998/simponi.v0i0.519 asra, t. (2019). komparasi algoritma c4.5, k-nn dan naïve bayes dalam penerimaan karyawan menggunakan pso pada pt. xyz. indonesian journal on software engineering (ijse), 5(2), 71– 79. https://doi.org/10.31294/ijse.v5i2.6959 bayu ferdiansyah, l. goeirmanto. (2020). prediksi loyalitas dalam keterikatan karyawan terhadap perusahaan menggunakan algoritma. jurnal sistem dan teknologi informasi, 8(1), 87– 97. chandra naya, m. (2019). analisa algoritma naïve bayes untuk klasifikasi karyawan teladan pada pt. toyoseal indonesia. sigma jurnal teknologi pelita bangsa, 10(2407–3903), 39– 45. herry derajad, w (2020). implementasi data mining dengan algoritma naïve bayes pada penjualan obat. jurnal informatika, vol 7 no 1 april, 1-7. ikhsan romli, a. t. z. (2020). penentuan jadwal overtime dengan klasifikasi data karyawan menggunakan algoritma c4.5. jurnal sains komputer & informatika (j-sakti), 4(september), 694–702. larose, d. t. (2014). discovering knowledge in data : an introduction to data mining. (i. new jersey: john wiley & sons (ed.)). marudut, v., siregar, m., komputer, t., indonesia, p. b., utara, s., cafe, e. s., cafe, s., & cafe, e. s. (2018). sistem pendukung keputusan penentuan insentif bulanan pegawai dengan menggunakan metode naïve bayes. 7, 87–94. noviyanto, a. s. (2018). prekdiksi turnover karyawan menggunakan metode klasifikasi naive bayes. v. prawitasari, a. (2016). faktor-faktor yang mempengaruhi turnover intention karyawan pada pt. mandiri tunas finance bengkulu. ekombis review: jurnal ilmiah ekonomi dan bisnis, 4(2), 177–186. https://doi.org/10.37676/ekombis.v4i2.283 rino gupitha. (2018). penerapan klasifikasi status pegawai menggunakan metode naïve bayes kajian teori penelitian terkait. jurnal global, v(1), 28–38. ryfa. (2020). teknik pengumpulan data kualitatif dan kuantitatif dalam metode penelitian. https://kumparan.com/berita-update/teknikpengumpulan-data-kualitatif-dan-kuantitatifdalam-metode-penelitian-1ukfvn1fwgs/full sahputra, d. a., & saelan, m. r. r. (2020). penentuan faktor kelayakan penerimaan karyawan menggunakan algoritma decission tree pada perusahaan pt . personel alih daya. jurnal sains dan informatika, 6(november), 148–156. https://doi.org/10.34128/jsi.v6i2.225 saleh, a. (2015). implementasi metode klasifikasi naïve bayes dalam memprediksi besarnya penggunaan listrik rumah tangga. creative information technology journal, 2(3), 207–217. sembiring, i. (2018). pengambilan keputusan pegawai tidak tetap menjadi pegawai tetap dengan decission tree. journal of informatics education, 1, 26–37. sugiyono. (2013). metode penelitian kuantitatif, kualitatif dan r&d. sunarti. (2019). prediksi promosi jabatan karyawan dengan algoritma c4 . 5 ( studi kasus : apartemen senayan jakarta ). techno.com, 18(4), 288–298. triuli novianti, i. s. (2016). penentuan jadwal kerja berdasarkan klasifikasi data karyawan menggunakan metode decision tree c4 . 5 ( studi kasus universitas muhammadiyah surabaya). jurnal komunikasi, media dan informatika, 5(1). http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 3 june 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i3.137 101 the work is distributed under the creative commons attribution-noncommercial 4.0 international license analysis of customer satisfaction on service arthaspa service with approach algorithm c4.5 sofian wira hadi1*, wawan kurniawan2, kudiantoro widianto3, ibnu alfarobi4 1,2computer science 1,2stmik nusa mandiri www.nusamandiri.ac.id 114002361@nusamandiri.ac.id ; 214002315@nusamandiri.ac.id ; 3,4accounting information systems 3,4bina sarana informatics university www.bsi.ac.id 3kudiantoro.kdw@bsi.ac.id; 4ibnu.iba@bsi.ac.id (*) corresponding author abstract customer or buyer satisfaction is closely related to how a seller of services or a store serves its visitors. good service for visitors also makes a good impression from visitors, while if the opposite will cause a very bad or unfavorable impression in the eyes of customers, and may also lead to the reluctance of visitors to come back lost the seller's opportunity to get potential buyers to become customers. this study attempts to analyze customer satisfaction with the services provided by arthaspa outlets in grand kemang hotels using the c4.5 algorithm approach. the attributes used are comfort, cleanliness, tidiness, and price. samples taken are customers who have transacted at least once.. keywords: data mining, c4.5, classification, arthaspa abstrak kepuasan pelanggan atau pembeli setuju dengan layanan penjual atau penyedia layanan yang melayani pengunjungnya. layanan yang baik untuk pengunjung yang menarik perhatian kedua pengunjung, sementara sebaliknya akan menarik perhatian yang lebih baik atau kurang di mata pelanggan, dan mungkin juga menarik pengunjung yang datang kembali untuk membeli kesempatan membeli pembeli yang berpotensi mendapatkan pelanggan. penelitian ini mencoba menganalisis kepuasan pelanggan dengan layanan yang disediakan oleh outlet arthaspa yang tersedia di grand kemang hotel menggunakan algoritma c4.5. atribut yang digunakan adalah kenyamanan, kebersihan, kerapian, dan harga. sampel yang diambil adalah pelanggan yang pernah bertransaksi sekali. studi ini mendapatkan kesimpulan paling populer tentang simpul "harga" saat menggunakan microsoft excel dan "kebersihan" saat menggunakan perangkat lunak rapidminer. kata kunci: data mining, c4.5, klasifikasi, arthaspa. introduction the best quality of service to customers, will also affect the trust of customers to the company so that customers are satisfied with the services received and thus the customer will convey satisfaction to others, with this case makes the market share expands and the company will be superior to its competitors (afrizal, 2018). consumer satisfaction is a comparison between the services received and consumer expectations, consumers have assessed satisfaction or dissatisfaction with the level of expectations they create in mind. in a situation of dissatisfaction occurs if consumers after using the product or service purchased feel that performance does not match consumer expectations (alawiyah, 2018). quality of service is very important and closely related to customer satisfaction itself. with good service quality will give satisfaction from customers, while service quality is lacking or not good so it gives uncomfortable effect to the customer (sobandi, 2019) the data visit, and it is also possible that over time can cause customers to switch to other competitors (hartono, 2017)who has a similar business. the current tight competition also forces the seller or buyer to http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i3.137 jurnal riset informatika vol. 2, no. 3 june 2020 102 the work is distributed under the creative commons attribution-noncommercial 4.0 international license produce a good service so that it can satisfy the customer (budiarti, 2018). quality of service is very important and closely related to customer satisfaction. with a good quality of service will provide satisfaction from customers, while a quality of service that is lacking or not good will give an uncomfortable effect for consumers who come to visit, and it is also possible that over time it can cause customers to switch to other competitors who have similar businesses . the current competitive conditions also force sellers or buyers to produce good service so that they can satisfy customers. companies in knowledge of the market or customers have a positive correlation in sales performance (noyita, 2019). arthaspa also prioritizes customer satisfaction in marketing strategies for the advancement of its company because it is related to market share and customer retention(puung et al., 2014). besides arthaspa also prioritizes good performance by employees so that the assessment produced by consumers of the service is also good and it is very important for the company, because customer satisfaction is a pleasant response and can be fulfilled, while customer dissatisfaction is an unexpected disappointment (susi et al., nd). in this research, it is expected that the results of customer satisfaction will be analyzed using the data mining approach c4.5 because the c4.5 algorithm is easy to understand and interpreted in its use (eki, 2016). to find out whether artspa has provided services that are in accordance with customer wishes. so the evaluation needs to be done from the customer side considering the attributes of comfort, cleanliness, tidiness, and price are very important in providing satisfaction to customers. research methodology knowledge discovery in database (kdd) data mining or knowledge discovery in database (kdd). the kdd process is the result of minimal data extracting a data pattern, and altering the results so that they are easy to understand(riandari & simangunsong, 2019). in kdd there are six most basic elements in kdd information retrieval techniques, namely: 1. working on data that will be processed with many sources. 2. efficient use of data is required 3. prioritizing statutes 4. requires high level of language usage 5. use several forms of automatic learning 6. produce unique results the knowledge discovery in database (kdd) process can be outlined as follows (yunita, 2018) : 1. data selection is the process for selecting words from a collection of data, data selection is done before the stage of obtaining an information in kdd. the results of the data selection will be stored in a file, separate from the database pre-processing or cleaning is before the data mining process is carried out, it is necessary to clean up the data that is the focus of kdd. the cleaning process includes removing duplicate data, checking for inconsistent data, and correcting data errors; 2. transformation is performed on data that has been selected or selected. so that the data selected is in accordance with the provisions of the data mining process. 3. data mining is the science of finding interesting patterns or information in large amounts of data by using certain techniques or methods. techniques, methods or algorithms in data mining vary widely. the choice of data mining method is very dependent on the kdd process (mardi, 2017). 4. interpretation or evaluation resulting from the data mining process really needs to be defined in a form that is easy to understand by interested parties. this stage is one part of the kdd process called interpretation. this stage as an evaluation of whether the pattern or information found is contrary to the previous hypothesis. data mining data mining is the science of extracting information from big data, in accordance with the purpose of data mining, which is to make a decision from a large data and stored in a database, data warehouse or information stored from a repository (tarigan et al., 2017). data collection data collection method is done by observation directly and use the questionnaire in getting accurate data. 1. observation is done by collecting a number of sales data by visiting directly the hotel in collaboration with cv. artha gemilang to get the information needed related to research. 2. questionnaire where the researcher distributes a list of questions to respondents regarding various aspects related to the value of each customer satisfaction attribute which will later be carried out on the results of research and discussion. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 3 june 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i3.137 103 the work is distributed under the creative commons attribution-noncommercial 4.0 international license research population the population that will be used is the total number of customers at outlets that work with cv, artha spa since the beginning of january 2019 until the end of june 2019 who have done at least once. ie as many as 186 people. research sample determination of the number of study samples is calculated by the slovin formula (luvia et al., 2017): n = n 1+ne2 ............................................................................. (1) where: n: number of samples n: total population e: error tolerance limit of 5 percent or 0.05. number of respondents to use: n = 200 1 + (200 ∗ 0,0025) yields n = 133.33, if rounded to 133. so the number of respondents used is 127 people. data analysis method the steps taken in data analysis include: 1 the results of the respondents' answers in the questionnaire were converted into a likert scale 2 obtained likert scale then to make a decision tree with the c4.5 algorithm approach. begin by forming which attribute will become root, or which root attribute will be based on the highest gain gain. if the value of an attribute has not resulted in a unanimous decision, then a recalculation is made by making a new branch under the previous node, but if a unanimous decision has occurred, then the calculation will be stopped and a final conclusion obtained. 3 the results of the algorithm calculation are then represented as a decision tree shape. research results and discussion as for the research on arthaspa using premiere data taken from may to june 2019 for the results of the questionnaire can be seen in table 1: table 1. questionnaire results no attribute number of cases yes not total 50 32 18 1 convenien ce very comfortable 31 27 4 enough 10 5 5 less comfortable 9 0 9 no attribute number of cases yes not total 50 32 18 2 cleanlines s clean 41 32 9 not clean 9 9 9 3 neatness neat 29 23 6 not neatly 21 9 12 4 price affordable 22 22 0 relatively inexpensive 24 7 17 expensive 4 3 1 evaluation and validation evaluation and validation are the results of the classification of data that has been determined based on the process used, henceforth after knowing the evaluation of the classification model based on the number of dataset records that have been predicted correctly and incorrectly in the classification modeling, these results can be known as confusion matrix. after getting a number of attributes, the next step is processing the selection of attributes(santoso, 2014). this attribute selection is done to get the attributes whose values are relevant. the following explanation of the attributes used: 1. convenience is an attribute given to respondents to assess comfort in service and is grouped into 3 categories, namely, very comfortable, quite, less comfortable. 2. cleanliness is an attribute to assess the cleanliness of the environment in the artha spa, and is grouped into 2 categories, clean and unclean. 3. neatness is an attribute that assesses the neatness of arthaspa employees who are grouped into 2 categories, neat and untidy. 4. price is an attribute of the price offered by artha spas to consumers, and is categorized into 3, namely affordable, relatively inexpensive and expensive. in this research the test results can be seen from the following steps: information gain and entrhopy the first step to do is calculate the entropy value and information gain data in table 2: table 2. entrhopy and gain values for all attributes attribute amoun t (s) yes (si) no (si) entrho phy gain total 50 32 18 0.9426 83 convenience 0.398 721 very 31 27 4 0.5547 http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i3.137 jurnal riset informatika vol. 2, no. 3 june 2020 104 the work is distributed under the creative commons attribution-noncommercial 4.0 international license attribute amoun t (s) yes (si) no (si) entrho phy gain comfortable 78 enough 10 5 5 1 less comfortable 9 0 9 0 cleanliness 0.320 077 clean 41 32 9 0.7592 76 not clean 9 9 9 0 neatness .1022 92 neat 29 23 6 0.7355 09 not neatly 21 9 12 0.9852 28 price 0.459 766 affordable 22 22 0 0 relatively inexpensive 24 7 17 0.8708 64 expensive 4 3 1 0.8112 78 table 3. price attributes attribute amoun t (s) yes (si) no (si) entrho phy gain total 50 32 18 0.9426 83 price 0.459 766 affordable 22 22 0 0 relatively inexpensive 24 7 17 0.8708 64 expensive 4 3 1 0.8112 78 in table 3 the price attributes have 3 categories, namely, affordable, relatively cheap, expensive. with each entrapping value. because the affordable category has a value of 0, what we are looking for in the next node is relatively cheap and expensive, it can be seen in table 4: table 4. relatively cheap attribute amoun t (s) yes (si) no (si) entrho phy gain total 50 32 18 0.9426 83 convenience 0.766 425 very comfortable 10 7 3 0.8812 91 enough 5 0 5 0 less comfortable 9 0 9 0 cleanliness 0.626 299 clean 16 7 9 0.9886 99 not clean 8 0 8 0 neatness 0.581 891 neat 5 0 5 0 attribute amoun t (s) yes (si) no (si) entrho phy gain not neatly 19 7 12 0.9494 52 the results of searching for the relatively inexpensive category price attribute yielded the highest gain value, namely comfort with a value of 0.766425. for further searching for the gain value for the convenience attribute, can be seen in table 5: table 5. comfort attribute total qty (s) yes (si) no (si) entropr gain 50 32 18 0.942683 cleanliness 0.942683 clean 7 7 0 0 not clean 3 0 3 0 neatness 0.766425 neat 0 0 5 0 not neatly 10 7 3 0.881291 the results of looking for comfort attributes produced the highest gain value, namely cleanliness with a value of 0.942683. because the entropy value of the comfort category 0 for the next calculation is to find the gain value from the expensive category, it can be seen in table 6: table 6. expensive categories total attribute number (s) yes (si) no (si) entrapr gain 50 32 18 0.942683 convenience 0.877781 very comfortable 4 3 1 0.811278 enough 0 0 0 0 less comfortable 0 0 0 0 cleanliness 0.942683 clean 3 3 0 0 not clean 0 0 0 0 neatness 0.877781 neat 4 3 1 0.811278 not neatly 0 0 0 0 search results from the expensive category produced the highest gain value, namely cleanliness with a value of 0.942683. because the entrhopy value of the comfort category 0 for the node calculation is complete. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 3 june 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i3.137 105 the work is distributed under the creative commons attribution-noncommercial 4.0 international license decision tree figure 1. decision tree results the results of the decision tree modeling in figure 1 shows that all cases are included in the class determined and therefore the decision tree is the final decision tree. after the results of modeling with the decision tree the creation of rules in the decision tree. the rules that can be formulated are as follows: "if cleanliness = not clean then class = not satisfied" "if cleanliness = clean and comfort = very comfortable, class = satisfied" "if cleanliness = clean and comfort = less comfortable then class = not satisfied" "if cleanliness = clean and comfort = enough and price = relatively cheap, class = not satisfied "if cleanliness = clean and comfort = enough and price = affordable, class = satisfied" the results obtained in the sample data that are rooted are the service attributes in the decision tree, while attributes such as comfort, cleanliness and price are good food. from the sample data, the number of rules used formed 5 rules. conclusions and suggestions conclusion from the results obtained in the previous discussion, conclusions can be drawn, with the attributes used such as: comfort, cleanliness, tidiness and price greatly affect the level of customer satisfaction. if cleanliness is not clean then the customer will be dissatisfied if the cleanliness is clean and very comfortable then the customer will be satisfied but if the cleanliness of the comfort level is sufficient and the price is affordable then the customer will be satisfied with the existing services. suggestion it needs to be evaluated and recalculated regularly so that the company can continue to optimize its services to customers. it is recommended to do another algorithm approach, included in the classification category and seen the highest level of accuracy in order to be taken into consideration for analyzing the next level of customer satisfaction. and of course it can also be a constructive suggestion reference list afrizal, b. (2018). the effect of service quality and price on customer satisfaction at warung mbah ganis. master of management, nusantara business institute, 1, 10-18. alawiyah, t. (2018). the influence of service quality on consumer satisfaction staying at diamond hotels in samarinda city. ejournal of business administration, 6 (2), 803–817. budiarti, a. (2018). the effect of service quality and complaint handling on customer satisfaction and loyalty of sharia commercial banks in anindhyta budiarti. equity, 15 (110), 210-231. eki, rm (2016). customer satisfaction analysis using c4 algorithm. 5. faculty of computer science, 3 (2), 1–14. hartono, a. (2017). analysis of service quality influence on customer satisfaction in forming customer loyalty in the naked crab restaurant surabaya. journal of hospitality and services management, 5 (2), 174–187. luvia, ys, windarto, ap, solikhun, s., & hartama, d. (2017). application of c4.5 algorithm for classification of student success predictions in amik tunas nation. jurasik (journal of information systems and informatics engineering research), 1 (1), 75. https://doi.org/10.30645/jurasik.v1i1.12 mardi, y. (2017). data mining: classification using c4.5 algorithm. journal of edict informatics, 2 (2), 213-219. noyita, e. (2019). measuring improvement of service quality and customer trust http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i3.137 jurnal riset informatika vol. 2, no. 3 june 2020 106 the work is distributed under the creative commons attribution-noncommercial 4.0 international license on customer satisfaction with sem analysis method (study at kampoeng spa batam. khazanah ilmu berazam, 2, 62-70. puung, fk, fudholi, a., & dharmmesta, bs (2014). analysis of the effect of service quality on customer satisfaction and loyalty in salons and spas. analysis of the effect of service quality on customer satisfaction and loyalty in salons and spas, 4 (2), 105-110. https://doi.org/10.22146/jmpf.274 riandari, f., & simangunsong, a. (2019). application of c4.5 algorithm to measure student satisfaction level. dikti accredited, 3 (2), 1–7. santoso, tb (2014). analysis and application of c4.5 method for predicting customer loyalty. limi's faculty of engineering scientific journal, 10 (1), 1–6. sobandi, mm (2019). service management in pharmacies p. bhakti kencana towards customer satisfaction. journal of pharmacopolium, 2 (1). https://doi.org/10.36465/jop.v2i1.468 susi, i., situmorang, s., nasari, f., systems, j., university, i., utama, p., & utama, up (nd). analysis of customer satisfaction with spa services with servqual (case study: pt. royal amadeus). december 2018, 521-528. tarigan, hd, destiawati, f., & fitriansyah, a. (2017). implementation of c4.5 algorithm towards customer satisfaction. ethos (journal of research and community service), vol. 6, no, 80–86. yunita, f. (2018). application of data mining using the k-means clustring algorithm on acceptance of new students. systemation, 7 (3), 238. https://doi.org/10.32520/stmsi.v7i3.388 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 2 maret 2019 p-issn: 2656-1743 e-issn: 2656-1735 91 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional penerapan metode profile matching sebagai pendukung keputusan pemilihan jurusan pada smk al hidayah fintri indriyani sistem informasi akuntansi universitas bina sarana informatika jakarta fintri.fni@bsi.ac.id abstrak pemilihan jurusan pada smk al hidayah dilakukan pada saat siswa/siswi mendaftar di sekolah tersebut, dengan acuan nilai minimal tiga mata pelajaran memenuhi standard minimal nilai yang telah ditetapkan pihak sekolah untuk tiap jurusan. penempatan jurusan dilakukan secara manual oleh panitia penerimaan siswa baru dengan melihat data nilai siswa dan minat siswa. hal ini memiliki kelemahan dari sisi waktu tidak efisien dan juga memungkinkan kesalahan input oleh panitia penerimaan siswa baru. sehingga diperlukan sebuah sistem berbasis komputer untuk membantu penentuan jurusan yang sesuai dengan kompetensi calon siswa. metode profile matching dalam penelitian ini digunakan untuk membantu mempercepat proses analisa kriteria nilai dan minat siswa disesuaikan dengan standard dari pihak sekolah. kriteria nilai meliputi nilai matematika, bahasa inggris dan bahasa indonesia, sedangkan pilihan jurusan ada akuntansi, administrasi perkantoran dan pemasaran. hasil penelitian adalah rekomendasi jurusan sehingga dapat mempercepat proses penjurusan sesuai dengan profile masing-masing siswa. kata kunci: evaluasi potensi, gap, profile matching, pemilihan jurusan, sistem pendukung keputusan. abstract the selection of majors at al hidayah vocational school is done when students enroll in the school, with a reference to a minimum of three subjects meeting the minimum standards of value set by the school for each department. placement of majors is done manually by the new student admission committee by looking at student grades and student interests. this has weaknesses in terms of inefficient time and also allows input errors by the new student admissions committee. so we need a computer-based system to help determine majors that are in accordance with the competencies of prospective students. the profile matching method in this study was used to help speed up the process of analyzing the value criteria and student interest according to the standards of the school. criteria for grades include math, english and indonesian languages, while the choice of majors is accounting, office administration and marketing. the results of the study are department recommendations so that they can accelerate the process of majors in accordance with the profile of each student. keywords: potential evaluation, gap, profile matching, selection of departments, decision support systems. pendahuluan sesuai dengan peraturan pemerintah no.29 tahun 1990 pasal 2 menyebutkan tujuan dari pendidikan menegah adalah meningkatkan pengetahuan siswa untuk melanjutkan pendidikan pada jenjang yang lebih tinggi dan untuk mengembangkan diri sejalan dengan perkembangan ilmu pengetahuan, teknologi dan kesenian dan meningkatkan kemampuan siswa sebagai anggota masyarakat dalam mengadakan hubungan timbalbalik dengan lingkungan sosial, budaya dan alam sekitarnya(kebudayaan, n.d.). pendidikan tingkat menengah di indonesia secara global terbagi menjadi dua yaitu sma dan smk dimana untuk siswa yang ingin segera terserap di dunia kerja kebanyakan memilih untuk masuk ke smk dikarenakan di smk siswa diberi pembekalan materi yang lebih aplikatif dan memfokuskan pada keterampilan siswa didik. smk al-hidayah yang berlokasi di cinere depok merupakan salah satu sekolah kejuruan yang memiliki tiga jurusan yaitu akuntansi, administrasi perkantoran dan pemasaran, dimana para calon siswa yang ingin masuk ke sekolah ini dapat memilih jurusan sesuai keinginan mereka. akan tetapi pihak sekolah juga memiliki standar minimum nilai yang digunakan untuk penempatan jurusan. selama ini panitia penerimaan siswa baru smk al-hidayah melakukan pendataan nilai dari tiga matapelajaran yaitu matematika, bahasa inggris dan bahasa indonesia dan http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 2 maret 2019 92 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional minat dari calon siswa, proses tersebut dilakukan secara manual (pratama, 2016). hal ini mengakibatkan proses penempatan jurusan menjadi lebih lama (prabowo, kusrini, & sunyoto, 2015) dan bisa jadi tidak sesuai dengan kompetensi calon siswa (susilawati, 2017) sehingga proses yang ada menjadi tidak efektif dan efisien (farida & firliana, 2016). berdasarkan permasalahan tersebut maka penelitian ini dilakukan dengan tujuan untuk membantu pihak sekolah dalam mempercepat proses penempatan jurusan sesuai dengan kompetensi siswa. pada penelitian terdahulu tentang pemilihan jurusan di perguruan tinggi stmik royal digunakan system pendukung keputusan menggunakan metode profile matching untuk memudahkan siswa dalam menentukam pilihan jurusan (yuma & rizaldi, 2018). ada pula pemilihan jurusan di man gresik menggunakan metode profile matching dan metode smarter untuk pembobotan tiap kriterianya lalu diuji cobakan dengan 200 data siswa di bandingkan dengan perhitungan manual dari pihak sekolah sehingga disimpulkan bahwa metode profile matching dapat dijadikan sebagai bahan pertimbangan dalam penentuan jurusan dengan hasil 67,41% keakuratan data (afifah, cahyani, & yunitarini, 2015). dalam implementasinya metode ini juga bisa di terapkan di berbagai kasus diantaranya sebagai sistem penunjang keputusan untuk kenaikan jabatan dengan penggunaan metode ini bias meminimalisir penilaian sepihak atau subyektifitas dan mengurangi kesalahan dalam meloloskan calon pegawai yang sesuai dengan standar perusahaan (frieyadie, 2016) dapat pula diterapkan pada pemilihan ketua jurusan dengan melihat factor-faktor kemampuan yang dimiliki calon ketua jurusan (anto & susilo, 2017). metode penelitian metode penelitian pada penelitian ini digunakan metode kuantitatif deskriptif untuk menentukan hubungan antara variabel dengan populasi dengan sekali pengukuran. metode pengumpulan data data diambil dari panitia penerimaan siswa baru pada smk al-hidayah yang merupakan data primer dengan metode wawancara dan dokumentasi. data yang disajikan merupakan data tahun ajaran 2018/2019. profile matching secara umum profile matching merupakan metode yang digunakan untuk membandingkan kompetensi objek penelitian dengan kompetensi yang diharapkan. dari selisih hasil perbandingan didapatlah gap, semakin kecil nilai gap maka terdapat peluang besar untuk nilai prioritas karena nilai bobot semakin besar. metode profile matching dapat digunakan untuk menyelesaikan masalah semi terstruktur. profile matching telah banyak digunakan dalam berbagai bidang untuk system pendukung keputusan diantaranya untuk penentuan kenaikan jabatan karyawan, pemilihan beasiswa, pemilihan mitra kerja termasuk juga pemilihan jurusan. tahapan penelitian penelitian ini dilakukan dengan tahapantahapan yang mengacu pada tahapan metode profile matching (kusrini, 2017) yang disesuaikan dengan objek penelitian yang ada, berikut adalah tahapannya: sumber: (indriyani, 2019) gambar 1. tahapan penelitian tahap pertama, penentuan kriteria profile ideal. pada tahap ini diambil nilai sebagai acuan di smk alhidayah untuk mata pelajaran matematika, bahasa indonesia dan bahasa inggris yang menjadi syarat minimal untuk tiap jurusan. tahap kedua, penentuan bobot per aspek. pada tahap ini nilai per aspek dari setiap calon siswa di data sesuai dengan acuan input nilai. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 2 maret 2019 p-issn: 2656-1743 e-issn: 2656-1735 93 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional tahap ketiga, pemetaan gap. menghitung gap dengan cara nilai mahasiswa per aspek dikurangi nilai profile ideal. kemudian ditentukan nilai bobot sesuai dengan table gap. tahap keempat, menghitung ncf dan nsf. ncf didapat dari rata-rata bobot nilai per aspek per calon siswa. nilai nsf didapat dari bobot nilai secondary factor. adapun rumus mencari ncf adalah: 𝑁𝐹𝐶 = ∑ 𝑁𝐶 (𝑎,𝑛) ∑ 𝐼𝐶 ……………..………………………. (1) dimana ncf = nilai rata-rata core factor nc(a,n)= jumlah total nilai core factor (matematika, bahasa indonesia dan bahasa inggris) ic= jumlah item core factor setelah nilai ncf dan nsf didapat maka dihitunglah nilai total dengan rumus 90% ncf ditambah 10%nsf dengan rumus sebagai berikut: 𝑁(𝑎, 𝑛) = (𝑥)% 𝑁𝐶𝐹(𝑎, 𝑛) + (𝑥)%𝑁𝑆𝐹(𝑎, 𝑛) ……. (2) dimana n(a,n) = total nilai aspek (x)% = nilai persen yang diinput ncf(a,n) = nilai rata-rata core factor nsf(a,n) = nilai rata-rata secondary factor tahap kelima. buat rekomendasi. pada tahap ini di data setiap calon siswa dibandingkan dan dipilih nilai terbesar sebagai rekomendasi. objek penelitian objek penelitian adalah smk al-hidayah yang didirikan pada tanggal 02 mei 1998 dibawah yayasan pendidikan islam al-hidayah cinere yang diketuai oleh h. abdullah h.m. pada awal berdirinya smk al-hidayah cinere dipimpin oleh bapak h.ardani m. nur sh, (alm). adapun 3 jurusan yang disediakan yaitu akuntansi, sekretaris , dan penjualan. akuntansi merupakan jurusan dengan minat terbanyak dan dengan nilai standar tertinggi dibandingkan dua jurusan yang lain. kemudian setelah berganti kurikulum jurusan tersebut berubah menjadi akuntansi, administrasi perkantoran, dan penjualan atau pemasaran. data diambil dari panitia penerimaan siswa baru sebanyak 67 calon siswa dari populasi 200 orang yang mendaftar di tahun ajaran 2018-2019 dengan menggunakan rumus slovin dengan tingkat error 10% (sugiyono, 2017) dengan penjabaran sebagai berikut: n = n / (1 + (n x e²)) n=200/(1+(200 x 0.12)) n=200/(1+(200 x 0,01)) n=200/3 n=66,6 atau dibulatkan menjadi 67 hasil penelitian dan pembahasan kriteria profile ideal untuk core factor sesuai dengan kondisi real di smk al-hidayah penjurusan dengan menimbang tiga nilai mata pelajaran yaitu nilai matematika, nilai bahasa inggris dan nilai bahasa indonesia, sedang untuk secondary factor digunakan minat calon siswa. pertama kita tentukan dulu nilai profile ideal, seperti dijabarkan di table 1 dan 2. tabel1. tabel acuan input nilai nilai sub kriteria range besar nilai < 64 1 65-74 2 75-84 3 85-94 4 95-100 5 sumber: (indriyani, 2019) tabel 2. tabel kriteria nilai profile ideal jurusan/mapel mtk bhs ing bhs ind akuntansi 2 2 2 administrasi perkantoran 1 2 2 pemasaran 1 1 2 sumber: (indriyani, 2019) penentuan nilai bobot per aspek nilai setiap aspek dari masing-masing jurusan dihitung dengan standard yang telah ditetapkan diawal oleh panitia penerimaan siswa baru untuk setiap calon siswa baru, ditabel 3 disajikan nilai dengan perbandingan profile ideal untuk jurusan akuntansi. langkah yang sama juga dilakukan untuk jurusan administrasi perkantoran dan pemasaran. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 2 maret 2019 94 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional tabel 3. data per aspek di jurusan akuntansi no nama siswa cf sf mtk bhs ing bhs ind minat siswa 1 nur amelia hasanah 3 3 3 1 2 diela ellandini 1 2 2 1 3 nabillah frana putri 3 1 2 1 4 fitriani apitah nurjanah 2 1 3 1 5 junaedi 2 2 2 1 6 ari munfako 2 1 1 2 7 raditya ludfianto 2 1 1 1 8 al-fath filsafah 3 3 2 3 9 rifaldy ahmad 2 1 1 2 10 ridwan hadi putra 1 3 1 3 profile ideal 2 2 2 1 sumber: (indriyani, 2019) pemetaan gap pada tahapan ini dibuat acuan gap dan bobot nilai dengan sesuai dengan pedoman tabel 4. tabel 4. tabel bobot nilai gap gap bobot nilai keterangan 0 3 kompetensi sesuai dengan profile ideal 1 3.5 kompetensi individu kelebihan 1 level -1 2.5 kompetensi individu kekurangan 1 level 2 4 kompetensi individu kelebihan 2 level -2 2 kompetensi individu kekurangan 2 level 3 4.5 kompetensi individu kelebihan 3 level -3 1.5 kompetensi individu kekurangan 3 level 4 5 kompetensi individu kelebihan 4 level -4 1 kompetensi individu kekurangan 4 level sumber: (indriyani, 2019) sehingga didapat nilai sebagai berikut untuk jurusan akuntansi. tabel 5. pemetaan gap no nama siswa gap bobot gap bobot gap bobot gap bobot 1 nur amelia hasanah 1 4,5 1 4,5 1 4,5 0 5 2 diela ellandini -1 4 0 5 0 5 0 5 3 nabillah frana putri 1 4,5 -1 4 0 5 0 5 4 fitriani apitah nurjanah 0 5 -1 4 1 4,5 0 5 5 junaedi 0 5 0 5 0 5 0 5 6 ari munfako 0 5 -1 4 -1 4 1 4,5 7 raditya ludfianto 0 5 -1 4 -1 4 0 5 8 al-fath filsafah 1 4,5 1 4,5 0 5 2 3,5 9 rifaldy ahmad 0 5 -1 4 -1 4 1 4,5 10 ridwan hadi putra -1 4 1 4,5 -1 4 2 3,5 sumber: (indriyani, 2019) perhitungan ncf dan nsf langkah selanjutnya adalah menghitung total core factor dengan menghitung rata-rata dari bobot nilai gap dari core factor dan membandingkan dengan secondary factor dengan perbandingan 90% untuk core factor dan 10% untuk secondary factor. seperti terlihat pada table 6. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 2 maret 2019 p-issn: 2656-1743 e-issn: 2656-1735 95 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional tabel 6 nilai ncf dan nsf untuk jurusan akuntansi no nama siswa cf sf nsk 1 nur amelia hasanah 3,6 3 3,6 2 diela ellandini 3,5 3 3,5 3 nabillah frana putri 3,1 3 3,1 4 fitriani apitah nurjanah 3,1 3 3,1 5 junaedi 3,8 3 3,7 6 ari munfako 3 4 3,1 7 raditya ludfianto 3 3 3 8 al-fath filsafah 3,8 5 3,9 9 rifaldy ahmad 3 4 3,1 10 ridwan hadi putra 3,4 5 3,5 sumber: (indriyani, 2019) rekomendasi langkah terakhir adalah membuat rekomendasi dengan cara membandingkan nilai akhir dari setiap jurusan dan hasil rekomendasi diambil dari nilai tertinggi. seperti terlihat di tabel 7. tabel 7. rekomendasi jurusan dengan metode profile matching no nama nsk ak nsk ap nsk pm rekomendasi 1 nur amelia hasanah 3,5625 3,3375 3,3375 1 2 diela ellandini 3,45 3,675 3,7875 3 3 nabillah frana putri 3,1125 2,8875 3,3375 3 4 fitriani apitah nurjanah 3,1125 3 3,45 3 5 junaedi 3,675 3,5625 3,675 1 6 ari munfako 3,1 2,9875 3,4375 3 7 raditya ludfianto 3 2,8875 3,3375 3 8 al-fath filsafah 3,875 3,65 3,65 1 9 rifaldy ahmad 3,1 2,9875 3,4375 3 10 ridwan hadi putra 3,5375 3,7625 3,7625 3 sumber: (indriyani, 2019) simpulan dan saran simpulan penerapan metode profile matching dalam menentukan jurusan pada smk al-hidayah dapat menghasilkan rekomendasi jurusan sesuai profile standar yang ditentukan pihak sekolah, dengan menghitung nilai gap kompetensi siswa dan standard ideal. sehingga dalam menentukan jurusan tidak hanya berdasarkan pilihan dari siswa seperti yang berlangsung saat ini, sehingga didapat hasil yang lebih baik dan efektif. dengan adanya penelitian ini panitia penerimaan siswa baru pada smk al-hidayah diberikan kemudahan dalam menentukan jurusan untuk calon siswanya sehingga proses pendataan menjadi lebih cepat. saran untuk pengembangan lebih lanjut dan agar pihak sekolah mudah dalam penggunaan metode ini maka perlu dibuat sebuah aplikasi dengan acuan metode profile matching. apabila dirasa perlu dapat dikembangkan menjadi expert system. daftar referensi afifah, n., cahyani, a. d., & yunitarini, r. (2015). sistem pendukung keputusan penentuan jurusan untuk siswa man gresik dengan metode profile matching. jurnal sistem informasi indonesia, 1(1). retrieved from http://www.publications.aisindo.org/index.ph p/jsii/article/view/4 anto, a., & susilo, t. (2017). penerapan metode profile matching pada sistem pendukung keputusan pemilihan ketua program studi ( studi kasus : program studi teknik informatika stmik musi rawas ), v(november), 87–93. farida, i. n., & firliana, r. (2016). implementasi metode profile matching untuk evaluasi potensi akademik penjurusan siswa man 2 kota kediri. jurnal infotel informatika telekomunikasi elektronika, 8(2), 156. https://doi.org/10.20895/infotel.v8i2.121 frieyadie, f. (2016). penggunaan metode profile matching untuk sistem penunjang keputusan kenaikan jabatan pada instansi pemerintah. paradigma jurnal komputer dan informatika, 18(2), 75–80. https://doi.org/10.31294/p.v18i2.1228 indriyani, f. (2019). laporan akhir penelitian: sistem pendukung keputusan pemilihan jurusan pada smk al hidayah. jakarta. kebudayaan, k. p. dan. (n.d.). peraturan pemerintah http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 2 maret 2019 96 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional no.29 tahun 1990 tentang pendidikan menengah. kusrini. (2017). konsep dan aplikasi sistem pendukung keputusan. yogyakarta: andi + amikom. prabowo, y. s., kusrini, k., & sunyoto, a. (2015). sistem pendukung keputusan pemilihan jurusan snmptn bagi siswa sman 7 purworejo. in proceedings konferensi nasional sistem dan informatika (kns&i) (vol. 0, pp. 180–185). bali: stmik stikom. retrieved from http://www.ejournal.stikombali.ac.id/index.php/knsi/article/view/438 pratama, r. p. (2016). sistem pendukung keputusan penjurusan siswa pada sman 5 kediri dengan menggunakan metode profil matching. universitas nusantara pgri kediri. retrieved from http://simki.unpkediri.ac.id/mahasiswa/file_a rtikel/2016/11.1.03.03.0230.pdf sugiyono. (2017). metode penelitian kuantitatif, kualitatif, dan r&d. bandung: alfabeta. susilawati, s. (2017). perangkat lunak berbasis website untuk membantu pemilihan jurusan di smk negeri 10 pandeglang. in prosiding seminar nasional riset terapan | senasset (pp. 26–32). serang: universitas serang raya. retrieved from http://ejurnal.lppmunsera.org/index.php/senasset/ar ticle/view/420 yuma, f. m., & rizaldi, r. (2018). sistem pendukung keputusan dalam pemilihan jurusan di perguruan tinggi dengan metode profile matching. seminar nasional royal (senar), 1(1), 181–184. retrieved from https://jurnal.stmikroyal.ac.id/index.php/sen ar/article/view/164 http://creativecommons.org/licenses/by-nc/4.0/ 29 analysis and design of mobile web-based menu e-order systems using the pieces method (case study: café 50/50 coffee) nabilah ananda pratiwi1), agung triayudi2*), endah tri esti handayani3) sistem informasi, fakultas teknologi komunikasi dan informatika universitas nasional 2018nabilah@student.unas.ac.id1), agungtriayudi@civitas.unas.ac.id2*), endahtriesti@civitas.unas.ac.id3) (*) corresponding author abstrak kafe sebagai tempat untuk melepas penat maupun bercengkerama dan pengunjung dapat melakukan pemesanan menu yang tersedia. pada umumnya sebuah kafe sering mengalami kesulitan dalam melayani pelanggan, terutama untuk fasilitas pemesanan menu. hal ini juga dialami oleh kafe 50/50 coffee yang masih melakukan pemesanan menu secara manual. berdasarkan permasalahan tersebut, dirancang sebuah sistem e-order menu aplikasi mobile berbasis web. penelitian ini bertujuan untuk menghasilkan sistem pemesanan mobile web yang kemudian dianalisis dengan indikator pieces untuk mendapatkan nilai kepuasan dari pengguna. perancangan sistem menggunakan metode pengembangan system development life cycle (sdlc) model waterfall kemudian dilakukan analisis tingkat kepuasan pengguna dengan metode pieces. pengujian sistem menggunakan usability testing dengan metode use questionnaire. implementasi sistem dibuat dengan bantuan framework codeigniter dan menggunakan bahasa pemrograman php. hasil penelitian berupa sistem e-order menu pada kafe 50/50 coffee dengan kesimpulan dari hasil analisis bahwa pengguna sistem e-order sudah merasa “puas”. kata kunci: sistem e-order, mobile web, metode waterfall, pieces framework, use questionnaire abstract café as a place to relax or chatter where visitors can order the menu available. in general, a café often has difficulty in serving customers, especially for menu ordering facilities. this is also experienced by café 50/50 coffee which still makes menu reservations manually. based on these problems, a system of e-order menus of web-based mobile applications is designed. the study aims to produce a mobile web ordering system that is then analyzed with the pieces indicator to determine the level of user satisfaction. design of this system using the waterfall model system development life cycle (sdlc) development method and then analyzed the level of user satisfaction with the pieces method. system testing uses usability testing with the use questionnaire method. system implementations are created with the help of the codeigniter framework and use the php programming language. the results of the study in the form of a menu e-order system at the 50/50 coffee café with the conclusion of the analysis that the users of the e-order system were “satisfied”. keywords: e-order system, mobile web, waterfall method, pieces framework, use questionnaire introduction information systems and technology are increasingly evolving so as to change the way and lifestyle also facilitate people in daily activities. technology is growing rapidly, so most people prefer to use technology in their activities. one of the example is internet and websites. website can help in terms of promoting a business, making it easier for customers to order menus and in order to win the competition (marudut & siregar, 2018). café as a place to relieve exhaustion or chatter where visitors can order the menu available (bastian, 2020). in addition to the menu offered, restaurant and café services in providing satisfaction to customers are also very influential on competition in the culinary business (triayudi & rodhi, 2018). café 50/50 coffee is one of the businesses in the culinary sector. this café is located at jalan nusantara no. 50, depok city, west java. during this time the booking facility is still done manually, i.e. visitors must do it directly mailto:2018nabilah@student.unas.ac.id mailto:agungtriayudi@civitas.unas.ac.id 30 through the cashier so that it can cause queues. this is less effective, especially during the covid-19 pandemic that is currently ongoing almost all over the world, including in indonesia. therefore, there is a rule that requires people to do social distancing to limit social activities in order to avoid physical contact and crowds (suherman et al., 2021). apart from that, there are other problems i.e. to find out information related to the menu in more detail or information about the availability of tables, visitors must directly come to the café. the menu e-order system at the café 50/50 coffee can make it easier for visitors to make table reservations and menu reservations more effectively and efficiently. then an analysis of user satisfaction levels with the pieces method is carried out in order to get an evaluation of a system that has been created before (julian, triayudi, & benrahman, 2021). as for the analysis conducted so that the e-order system can meet the qualifications in the pieces framework (tjiptabudi, 2017). this study aims to produce a mobile web ordering system which is then analyzed with the pieces method to find out the level of user satisfaction. with the food and beverage menu e-order system, it is expected to be useful to help visitors in ordering online. some previous research related to the development of menu e-order systems, in the study (fonggo, beng, & arisandi, 2020) the ordering system using the sdlc method with the waterfall model. program creation uses html and php also mysql as database storage. the results of the study in the form of a web-based payment and booking system implemented in the canteen. the research (manikam & ardiyansah, 2019) conducted a system design at bebek goreng haji yogi restaurant that utilizes the pieces method for problem analysis. system design uses balsamiq software with php programming language. the result of the study is in the form of the design of an e-order system. in research (dhiman, 2021) online food ordering management system used in the culinary field. website implementations are performed using php, html, css and datasets stored in the phpmyadmin sql database. the result is a website-based online food ordering system that will be applied in small restaurants and locations such as college canteens, etc. research (riswanda & priandika, 2021) about ordering system on the donnys store uses php programming languages and mysql databases also designed using uml (unified modeling language). system development utilizes waterfall methods and analyzes system needs with the pieces method. the results of the study are in the form of items order management applications. in the study (dzulfiqar, 2019) apply pieces analysis to the current system. by using uml as a system design. the results of this study are in the form of an application that makes it easier for customers to order food on bu sri’s food stalls. based on these studies, the authors built a food and beverage menu e-order system to be applied to café 50/50 coffee. system design applies the system development life cycle (sdlc) waterfall model method as well as the pieces framework method to determine the level of user satisfaction. as for testing using usability testing with the use questionnaire method. research methods types of research the type of research used by the authors is qualitative descriptive using data collection methods namely observation, interviews, and literature studies. time and place of research the study was conducted in october 2021 at the café 50/50 coffee. research target / subject the study focused on issues related to the ordering system at café 50/50 coffee. data collection methods the data was collected with observations related to the problems that occurred in the café 50/50 coffee and the collection of references obtained from previous studies to get an idea of the needs of the system to be made. questionnaires were also distributed to system users and interviews with the owners/employees of the café in order to produce accurate data. system development methods sdlc is a life cycle in software development. sdlc helps developers improve the quality of the software produced. sdlc emphasizes the needs of users and with a structured approach to building or developing new systems (rahayu, susanto, & suwarjono, 2020). waterfall method is included in the system development model by focusing on sequenced and systematic stages. waterfall method stages (muhammad robith adani, 2020): 1. requirement the first stage is to analyze the needs of the system to be built. information is obtained from observations, analysis with pieces framework 31 indicators, and interviews with the related café, as well as conducting literature studies. 2. design the next stage is the creation of a system design which is the process by which functional analysis of the system is applied to the unified modelling language (uml). 3. implementation the implementation stages of program code use visual studio code tools as text editors with the help of the codeigniter framework, also use the php programming language. in addition, the system is designed with some supporting software such as xampp. 4. integration & testing this stage aims to know the suitability of the system with the design, functionality of the system, and to prevent bugs or errors in the system. testing is done by applying usability testing method use questionnaire. 5. operation & maintenance after testing the system, then proceed to the system usage stage by the user (user). at this stage, the developer can make improvements if an error is found in the system that has been used by the user. methods of analysis the analysis method used is pieces framework which is a method to identify in order to solve problems that occur in the system against indicators performance, information, economy, control, efficiency, and service (salwa husna, fadli, & hajar, 2018). table 1. analysis of problem identification with the pieces method pieces indicators old system new system performanc e menu ordering is still done directly through the cashier. ordering takes a long time in choosing a menu, so it can cause queues. menu reservations can be made via smartphone which can be easily accessed by users before coming to the café. information customers need to come directly to get more information related to detailed order and menu and information related to order data and menu details also table availability is faster and easier to get pieces indicators old system new system also information about table availability. just by accessing the web. economy errors may occur regarding orders and total payments generated. menu ordering activities require more manpower. the order process, order details and total payment are processed automatically through the system. control data can be accessed by anyone, so security is less maintained. the process of managing data that is still manual takes a long time. existing data can only be accessed by the related admin. the data management process takes place quickly. efficiency the process of recapting data can takes a long time because recording is still done manually. the time required for the recap process is only a little because admins can directly access it on the system. service the exchange of information that occurs is still done directly. the exchange of information is more detail and fast because it is easily accessible online. data analysis was conducted from the questionnaires distribution to find out the level of user satisfaction with the e-order system involving 6 pieces indicators. respondents were involved as many as 20 people according to the range of café 50/50 coffee visitors every day. the study used the satisfaction level likert scale listed in table 2. table 2. satisfaction level likert scale answer options score strongly agree 5 agree 4 neutral 3 32 disagree 2 strongly disagree 1 table 3 is the assessment characteristic for the pieces framework method (ramadhani & kusuma, 2018). table 3. level of satisfaction categories value range very dissatisfied 1-1,79 not satisfied 1,8-2,59 quite satisfied 2,6-3,39 satisfied 3,4-4,91 very satisfied 4,92-5 testing methods the test used is the usability testing method use questionnaire, which consists of 4 aspects, namely usefulness, easy of use, easy of learning, and satisfaction (retnoningsih & fauziah, 2019). the test on this study involved 20 respondents from a population that is the range of visitors at a café 50/50 coffee every day. this is based on nielsen's theory that results with a large number of usability testing and with only 20 respondents will not be much different, so it will save more costs and time if the number of respondents is less (setiyani, syamsudin, gintings, & arifin, 2020). the test was conducted by distributing questionnaires by providing 5 alternative assessments using the likert scale as in table 2. then an average search is performed for each respondent's answer and performs interval calculations as in equation 1. interval (i) = 100 jumlah skor (likert) ................................. (1) interval (i) = 100 5 = 20 from the results of the interval can be categorized in the eligibility table contained in table 4. table 4. eligibility category eligibility category score (%) very useless <21 not useful 21-40 quite useful 41-60 useful 61-80 very useful 81-100 results and discussion requirements the café menu e-order system has 2 levels of users, namely visitors who want to order at the café and admin. 1. café visitors visitors can view the available menus, order menus, manage orders, receive confirmations and order details. 2. admin admins who also act as cashiers can login, manage master data, monitor desks, manage orders, confirm arrivals and payments of visitors, print proof of payment, and perform logout. system design a. system menu scheme design figure 1. system main menu scheme in figure 1, it can be seen that the café 50/50 coffee menu e-order system has many menu features that are divided into two parts of the interface, namely the user side as a visitor and the admin side. both of these sections have interfaces, as well as different roles and menu features. the difference is that visitors can only access parts of the web interface. while admins can access, change, delete available data and set up a web interface. b. use case diagram figure 2. use case diagram 33 in figure 2 there is a use case diagram proposed as a depiction of the functionality of eorder system. there are two actors who interact with the system, namely admin and user. such interactions are like viewing, ordering, inputting, confirming order data for user and processing data, order, and user for admin. c. activity diagram in figure 3 there is an activity diagram that contains the ordering activity in ordering through the e-order menu system. starting from the booker who sees and selects the menu you want to order until the payment process. figure 3. activity diagram system interface implementation 1. admin page – login page view figure 4. login page in figure 4 displays the login page, where an admin needs to enter his username and password to be able to enter the application. admins who have successfully logged in and entered the application, will go to the dashboard page. 2. admin page – dashboard page view 34 figure 5. dashboard page in figure 5 there is a dashboard page where admins can monitor the number of menus that are currently available, revenue per month and total overall revenue. 3. user page – menu details view figure 6. menu details page figure 6 displays the menu details page listed photos, descriptions, length of creation and price as well as the number of menus that visitors want to order. 4. user page – order menu view figure 7. order menu page in figure 7 displays the order basket from the menu that the visitor has chosen to order. on this page visitors can still change the number and delete the order that has been selected. system analysis a. results of calculation and analysis of user satisfaction levels the assessment of user satisfaction levels of the e-order menu system uses a likert scale such as table 2 based on questionnaires distributed to 20 respondents. the method used is pieces with the formula of the average level of satisfaction (rk) of the system as in equation 2. rk = number of questionnaire scores number of questionnaires (2) here are the results of the questionnaire calculations of each pieces indkator as in table 5. table 5. results of satisfaction level of pieces indicator pieces indicators average satisfaction (rk) score performance 4,35 satisfied information 4,43 satisfied economics 4,27 satisfied control 4,33 satisfied efficiency 4,48 satisfied service 4,5 satisfied total 4,39 satisfied 35 the results of the calculation of average satisfaction (rk) users on the performance indicator get a value of 4.35 then based on the level of satisfaction in table 3 can be categorized as satisfied. in the information indicator gets a value of 4.43 then it can be categorized as satisfied. in the economics indicator gets a value of 4.27 then the economic value indicator can be categorized as satisfied. in the control indicator gets a value of 4.33 then it can be categorized as satisfied. in the efficiency indicator gets 4.48 then it can be categorized as satisfied. on the service indicator gets 4.5 then it can be categorized as satisfied. based on these results, it can be concluded that users of the menu e-order system at café 50/50 coffee are satisfied. system testing a. measurement of usability with use questionnaire method testing was conducted by spreading questionnaires that adopted questions related to 4 aspects of the use questionnaire. questionnaires were distributed to prospective users of the café 50/50 coffee e-order system as many as 20 respondents. respondents accessed the e-order system and used it, then filled out a questionnaire by giving an assessment according to the likert scale in table 2. the measurement of usability is obtained by calculating the percentage of answers from all respondents as in equation 3. the number of observed scores was obtained by calculating the results of all respondents's answers to each aspect which was then multiplied by each score using the likert scale. the number of expected scores obtained from the highest value of the likert scale is multiplied by the number of respondents and then multiplied by the number of questions each aspect of usability. pk (%) = observed score expected score × 100 ..................................... (3) the results of usability measurements can be seen in table 6, then obtained calculations and percentage eligibility (pk). table 6. usability aspect measurement results aspects of usability respondent score max score (%) usefulness 694 800 86,7% easy of use 945 1.100 85,9% easy of learning 345 400 86,2% satisfaction 602 700 86% total 2.586 3.000 86,2% the results of measurements on the usefullness aspect obtained a percentage of 86.7% then the conclusion obtained that the e-order system of café 50/50 coffee menu is very useful. the results of measuring easy of use aspects obtained a percentage of 85.9% then the conclusion obtained that the e-order system of café 50/50 coffee menu is very easy to use. the results of the measurement of easy of learning aspects obtained a percentage of 86.2% then the conclusion obtained that the e-order system of café 50/50 coffee menu is very easy to learn. the results of measurements in the satisfaction aspect obtained a percentage of 86% then the conclusion obtained that the e-order system of café 50/50 coffee menu is very satisfying for users. the score observed from the total score of answers came from 20 respondents, which was 2,568, while the expected score was 3,000. based on these results, it was obtained a measurement of 86.2% which in table 3 is at intervals of 81-100% so that the results of measuring the usability of the café 50/50 coffee menu e-order system are classified "very useful". conclusions and suggestions conclusion café 50/50 coffee menu e-order system designed with waterfall method and uses pieces method for user satisfaction level analysis. based on the results of the analysis of the calculation of the average amount of satisfaction level of 4.39, it can be concluded that users of the e-order menu system at café 50/50 coffee are satisfied. while the results of usability measurement of 86.2% which shows that the e-order system of café 50/50 coffee menu is classified as very useful. suggestion based on the conclusions obtained, there are several suggestions that can later be done for future research that researchers can add other features in the e-order menu system, such as installing payment gateways for payment processes. further research can also add and develop analytical and testing methods with other methods. references bastian, r. a. (2020). perancangan aplikasi pemesanan makanan dan minuman pada cafe ungu berbasis web pada jaringan intranet. universitas islam sultan agung semarang. dhiman, k. (2021). online food ordering management system. international journal for 36 research in applied science and engineering technology, 9(vii), 2096–2107. https://doi.org/10.22214/ijraset.2021.3683 5 dzulfiqar, m. a. a. (2019). sistem informasi pemesanan makanan berbasis android dengan teknologi webview di warung makan bu sri. universitas duta bangsa. fonggo, f., beng, j. t., & arisandi, d. (2020). webbased canteen payment and ordering system. iop conference series: materials science and engineering, 1007(1). iop publishing ltd. https://doi.org/10.1088/1757899x/1007/1/012159 julian, b., triayudi, a., & benrahman. (2021). user satisfaction analysis for event management systems using rad and pieces framework. iop conference series: materials science and engineering, 1088(1), 012024. https://doi.org/10.1088/1757899x/1088/1/012024 manikam, r. m., & ardiyansah, m. (2019). prototype e-order pada restoran bebek goreng haji yogi menggunakan metode pieces. jurnal ilmiah fifo, 11(2), 189. https://doi.org/10.22441/fifo.2019.v11i2.00 8 marudut, v., & siregar, m. (2018). perancangan website sebagai media promosi dan penjualan produk. technology acceptance model, 9(1), 15–21. muhammad robith adani. (2020, december). tahapan pengembangan perangkat lunak dengan metode waterfall. rahayu, t. k., susanto, & suwarjono. (2020). application report process of islamic school based on pesantren boarding using waterfall model. journal of physics: conference series, 1569(2). iop publishing ltd. https://doi.org/10.1088/17426596/1569/2/022025 ramadhani, s., & kusuma, w. a. (2018). pieces framework untuk analisa tingkat kepuasan pengguna dan kepentingan sistem informasi. in jurnal teknologi & manajemen informatika (vol. 4). retnoningsih, e., & fauziah, n. f. (2019). usability testing aplikasi rekomendasi objek wisata di provinsi jawa barat berbasis android menggunakan use questionnaire. bina insani ict journal, 6(2), 205–216. riswanda, d., & priandika, a. t. (2021). analisis dan perancangan sistem informasi manajemen pemesanan barang berbasis online. jurnal informatika dan rekayasa perangkat lunak (jatika), 2(1), 94–101. salwa husna, s., fadli, m., & hajar, d. (2018). rancang bangun sistem pemesanan tiket bus berbasis mobile pada perusahaan otobus di dumai. jurnal resti (rekayasa sistem dan teknologi informasi), 2(3), 611–620. setiyani, l., syamsudin, a., gintings, a., & arifin, d. (2020). the analysis of functional needs on undergraduate thesis information system management. international journal of advances in data and information systems, 1(2). https://doi.org/10.25008/ijadis.v1i2.184 suherman, a., tetep, t., mulyana, e., supriyatna, a., widyanti, t., saripah, o., … purnawati, l. (2021). persepsi masyarakat terhadap pemberlakuan social distancing di masa pandemi covid-19 sebagai implementasi modal sosial. business innovation and entrepreneurship journal, 3(02), 135–140. https://doi.org/10.35899/biej.v3i02.218 tjiptabudi, f. m. h. (2017). analisis dan perancangan e-business berbasis website menggunakan pieces framework (studi kasus: aspin photography & video pro). jurnal hoaq – teknologi informasi, 8(1), 603–679. triayudi, a., & rodhi, a. s. (2018). waterfall modelling pada sistem e-restorant. jurnal protekinfo, 5, 2406–7741. 87 image enhancement on object detection using l0 gradient prior sunario megawan1*), hernawati gohzali2, apriyanto halim3 program studi teknik informatika universitas mikroskil https://www.mikroskil.ac.id/ 1*)sunario@mikroskil.ac.id, 2hernawati.gohzali@mikroskil.ac.id, 3apriyanto.halim@mikroskil.ac.id (*) corresponding author abstrak pendeteksian objek merupakan teknik yang digunakan untuk mengambil bagian-bagain tertentu pada citra. bagian tersebut dapat berupa pemandangan, manusia atau benda-benda lainnya. pada saat pendeteksian objek, citra yang didapatkan dapat mengalami penurunan kualitas citra yang dapat diakibatkan dari faktor cuaca, yaitu kabut, asap, debu, hujan dan lainnya. penurunan kualitas pada citra, dapat mengakibatkan kesalahan pada klasifikasi dan tidak mampuan dalam mengenali objek pada citra. oleh karena itu, proses perbaikan kualitas citra menjadi sangat penting untuk dilakukan pada saat tahap pre-processing dalam pendeteksian objek citra. fokus masalah yang akan diselesaikan pada penelitian ini adalah pengembali an citra kabur dengan menggunakan l0 gradient prior. hasil penelitian menunjukan penerapan l0 gradient prior dalam mengembalikan citra yang kabur dapat meningkat jumlah objek yang dapat diditeksi oleh sistem penditeksian objek. kata kunci: peningkatan kualitas citra, deteksi objek abstract object detection is a technique used to retrieve certain parts of the image. the part can be in the form of scenery, people, or other objects. at the time of object detection, the image obtained can experience a decrease in image quality which can be caused by weather factors, namely fog, smoke, dust, rain, and others. a decrease in the quality of the image can result in errors in classification and the inability to recognize objects in the image. therefore, the process of improving image quality becomes very important to do at the pre-processing stage in detecting image objects. the focus of the problem to be solved in this study is the return of a blurred image using l0 gradient prior. the results showed that the application of l0 gradient prior in rest oring a blurred image can increase the number of objects that can be detected by the object detection system. keywords: image enhancement, object detection introduction object detection is a technique used to retrieve certain parts of the image. the part can be in the form of scenery, humans or other objects (vidal, banerjee, grm, struc, & scheirer, 2018). when performing object detection, the image obtained can experience a decrease in image quality which can be caused by weather factors, like fog, smoke, dust, rain, and others (roy & bhowmik, 2021). decrease in image quality can also occur due to the process of increasing the size of the object in the image, thus making the image blurry or unclear. as for the consequences that can occur due to a decrease in image quality, namely errors in image classifiers or object suitability (borel-donohue & young, 2019). image quality degradation can also result in changes to information. changes in information that are too large of course result in a lot of information being lost in the image. image quality degradation may cause the system to not detect objects properly (hasirlioglu, reway, klingenberg, riener, & huber, 2019). this is of course very necessary for further processes in the form of object detection, angle detection and others. measurement of the level of change in the image before and after improving image quality can be seen from the success of object detection in the image. the method used in this research for object detection in the image is the faster r-cnn algorithm (ren, he, girshick, & sun, 2017). faster rcnn is the latest region-based generic object detection method that shows excellent results in various object detections (wu, yin, wang, & xu, 88 2019). several studies have shown that faster rcnn can detect objects well with an accuracy value of 7299% (gavrilescu, zet, fosalau, skoczylas, & cotovanu, 2018) (cai, li, xie, zhao, & lu, 2018) (chandan, jain, jain, & mohana, 2018)(zhang et al., 2020). several research methods have been carried out to restore blurred images, including the dark channel method (dark layer) which gives better results compared to other methods with a success rate of around 27.94 db (decibels) compared to other methods (pan, sun, pfister, & yang, 2018)(zhou, zhuang, xiong, zhao, & du, 2020). in another study conducted by (anger, facciolo, & delbracio, 2019) who used l0 gradient before restoring a blurred image. the research carried out gave the results obtained in the form of good performance which can be seen from several tests carried out in the form of various images and the addition of noise. based on the research reference, the method used in this research for restoring a blurred image is l0 gradient prior. the purpose of this research is to increase the accuracy of object detection in the image by adding a pre-processing stage in the form of improving image quality by returning a blurred image so that the object detection results are expected to have better accuracy and be able to recognize more objects in the image. research methods the research method used is l0 gradient prior to restore blurred images and faster r-cnn for object detection in video images. l0 gradient prior method consists of 3 simple stages, namely multiscale kernel estimation, sharp prediction, and kernel prediction. in figure 1, shows the flowchart of l0 gradient prior. faster r-cnn algorithm is divided into 2 important parts, namely the regional proposal network (rpn) and the classifier. rpn is used to find the input results in the image that allows the location of the object quickly. the results of the rpn process will later be made in the form of an roi (region of interest). the classifier is a process that classifies roi from the previous step into corresponding classes (abbas & singh, 2018). in figure 2, shows the flowchart of faster r-cnn. figure 1 l0 gradient prior flowchart figure 2 faster rcnn flowchart 89 types of research this research is related to computer visualization and image processing that deals with detecting examples of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. time and place of research in this study, the dataset is collected from seven intersections in the danish cities of aalborg and viborg. the resolution of cameras are 640x480 pixels and the frame rate is fixed at 20 frames/second. cctv video data on datasets taken at night were not used because the lighting conditions at night made object detection difficult. research target / subject the purpose of this research is to increase the accuracy of object detection in the image by adding a pre-processing stage in the form of improving image quality to eliminate blurred images, so that object detection results are expected to have better accuracy and be able to recognize more objects. procedure this type of research focuses on improving the quality of the image which will then proceed to the object detection process stage. improving the quality of the image is done through the process of returning the blurred image using l0 gradient prior. the results of the blurred image return process are then processed to the object detection stage with the faster r-cnn algorithm. after all, processes are successfully carried out, the stages of testing the results obtained using the confusion matrix are carried out. the next step is to compare the results of object detection accuracy before and after improving image quality. it aims to see the level of accuracy in this study. data, instruments, and data collection techniques the dataset used in this study is the aau rainsnow traffic surveillance dataset (bahnsen & moeslund, 2018). this dataset contains cctv video data that monitors road conditions in rainy and snowy conditions. data analysis technique in this study, we will use a cctv capture dataset in which there is a blurred image object. open cv library is used to convert a video into a series of images. furthermore, the series of images is processed to restore the blurred image using l0 gradient prior. furthermore, the data will be separated into two parts, namely data for training and data for testing. the test data are then analyzed to determine the accuracy of the research results using the confusion matrix. results and discussion result of l0 gradient prior the results of the implementation of blurred image improvement can be seen in figures 3 and 4. figure 3 shows a sample image on cctv video before the implementation of blurred image correction. in figure 4, after the process of correcting the blurred image using the l0 gradient prior algorithm, it looks sharper than figure 3. figure 3. sample image of cctv video before the implementation of blurred image correction figure 4. sample image of cctv video after the implementation of blurred image correction result of faster rcnn in this study, the object detection process is divided into two processes, namely the training process and the testing process. in the training process, objects trained on the system are limited to a minimum size of 50 x 50 pixels to reduce object 90 detection errors caused by the size of the trained object being too small. there were 2 (two) cctv video conditions observed, namely the condition of the cctv video that had not been processed to restore the blurred image and the condition of the cctv video that had gone through the process of returning the blurred image. examples of cctv video images that have been processed with faster rcnn can be seen in figure 5 and figure 6. figure 5 shows a sample image on cctv video before processing to restore the blurred image. figure 6 shows a sample image on cctv video after processing to restore the blurred image. the results of object detection on 2 (two) cctv video conditions can be seen in table 1. in table 1, tp represents the system successfully classifying objects moving vehicles on video correctly, fp represents the system incorrectly recognizing objects that are not vehicles but are recognized as vehicles, tn represents the system successfully correctly detects non-vehicle objects, and fn represents the system failed to detect moving vehicles as non-vehicle objects. figure 7 shows a sample image on cctv video after processing to restore the blurred image, the results of object detection with the faster rcnn algorithm show an error in object detection. figure 5. sample object detection image on cctv video before processing to restore the blurred image figure 6. sample object detection image on cctv video afterprocessing to restore the blurred image figure 7. sample image on cctv video after processing to restore the blurred image that has an error in object detection the results of table 1 then calculate the detection accuracy using the confusion matrix to measure the accuracy of the object detection results. the calculation results can be seen in table 2. based on the data in tables 1 and 2, it can be concluded that the accuracy of object detection decreased slightly when cctv video was given the process of returning a blurred image on video testing 1 but the number of objects detected by the system increased in test videos 1 and 2. tabel 1. object detection result in 2 cctv video condition video condition number of object detected test video 1 test video 2 tp fp tn fn tp fp tn fn video without deblur process 394 0 0 0 212 0 0 0 video with deblur 439 5 0 0 233 0 0 0 91 tabel 2. accuracy calculation result using the confusion matrix video condition confusion matrix result for accuracy value (%) test video 1 test video 2 video without deblur process 100 100 video with deblur process 98,87 100 conclusions and suggestions conclusion the accuracy of object detection decreased slightly when cctv video was given the process of returning a blurred image on video testing 1 but the number of objects detected by the system increased in test videos 1 and 2. this means that by applying the blur image return algorithm, the number of objects that can be recognized is more than without the application of the blur image return algorithm suggestion in this study, it is still not able to recognize objects with a size of less than 50 x 50 pixels so that in the future it is recommended to apply an algorithm to increase the size of the image so that small objects can still be detected. acknowledgement the researcher would like to thank the ministry of research and technology / national research and innovation agency (ristekbrin) who funded this research from start to finish to the publication stage. references abbas, s. m., & singh, s. n. (2018). region-based object detection and classification using faster r-cnn. 2018 4th international conference on computational intelligence & communication technology (cict), 1–6. ghaziabad: ieee. https://doi.org/10.1109/ciact.2018.84804 13 anger, j., facciolo, g., & delbracio, m. (2019). blind image deblurring using the l0 gradient prior. ipol journal · image processing on line, 9, 124–142. https://doi.org/doi.org/10.5201/ipol.2019.2 43 bahnsen, c. h., & moeslund, t. b. (2018, september 21). aau rainsnow traffic surveillance dataset. retrieved january 11, 2022, from kaggle website: https://www.kaggle.com/aalborguniversity/ aau-rainsnow/metadata borel-donohue, c. c., & young, s. s. (2019). image quality and super resolution effects on object recognition using deep neural networks. https://doi.org/10.1117/12.2518524, 11006, 596–604. baltimore: spie. https://doi.org/10.1117/12.2518524 cai, w., li, j., xie, z., zhao, t., & lu, k. (2018). street object detection based on faster r-cnn. chinese control conference, ccc, 2018-july, 9500–9503. https://doi.org/10.23919/chicc.2018.8482 613 chandan, g., jain, a., jain, h., & mohana. (2018). real time object detection and tracking using deep learning and opencv. proceedings of the international conference on inventive research in computing applications, icirca 2018, 1305–1308. https://doi.org/10.1109/icirca.2018.85972 66 gavrilescu, r., zet, c., fosalau, c., skoczylas, m., & cotovanu, d. (2018). faster r-cnn:an approach to real-time object detection. epe 2018 proceedings of the 2018 10th international conference and expositions on electrical and power engineering, 165–168. https://doi.org/10.1109/icepe.2018.85597 76 hasirlioglu, s., reway, f., klingenberg, t., riener, a., & huber, w. (2019). raindrops on the windshield: performance assessment of camera-based object detection. 2019 ieee international conference on vehicular electronics and safety, icves 2019. https://doi.org/10.1109/icves.2019.89063 44 pan, j., sun, d., pfister, h., & yang, m. h. (2018). deblurring images via dark channel prior. ieee transactions on pattern analysis and machine intelligence, 40(10), 2315–2328. https://doi.org/10.1109/tpami.2017.27538 04 ren, s., he, k., girshick, r., & sun, j. (2017). faster rcnn: towards real-time object detection with region proposal networks. ieee transactions on pattern analysis and machine intelligence, 39(6), 1137–1149. 92 https://doi.org/10.1109/tpami.2016.25770 31 roy, s. d., & bhowmik, m. k. (2021). annotation and benchmarking of a video dataset under degraded complex atmospheric conditions and its visibility enhancement analysis for moving object detection. ieee transactions on circuits and systems for video technology, 31(3), 844–862. https://doi.org/10.1109/tcsvt.2020.29911 91 vidal, r. g., banerjee, s., grm, k., struc, v., & scheirer, w. j. (2018). ug2: a video benchmark for assessing the impact of image restoration and enhancement on automatic visual recognition. proceedings 2018 ieee winter conference on applications of computer vision, wacv 2018, 2018-january, 1597–1606. https://doi.org/10.1109/wacv.2018.00177 wu, w., yin, y., wang, x., & xu, d. (2019). face detection with different scales based on faster r-cnn. ieee transactions on cybernetics, 49(11), 4017–4028. https://doi.org/10.1109/tcyb.2018.285948 2 zhang, j., karkee, m., zhang, q., zhang, x., yaqoob, m., fu, l., & wang, s. (2020). multi-class object detection using faster r-cnn and estimation of shaking locations for automated shakeand-catch apple harvesting. computers and electronics in agriculture, 173, 105384. https://doi.org/10.1016/j.compag.2020.10 5384 zhou, k., zhuang, p., xiong, j., zhao, j., & du, m. (2020). blind image deblurring with joint extreme channels and l0-regularized intensity and gradient priors. proceedings international conference on image processing, icip, 2020-october, 873–877. https://doi.org/10.1109/icip40778.2020.91 91010 jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 1 the work is distributed under the creative commons attribution-noncommercial 4.0 international license sentiment analysis of digital wallet service users using naïve bayes classifier and particle swarm optimization alvie delia cahyani1, tati mardiana2, laela kurniawati3 information system1.3; information technology2 stmik nusa mandiri1.3; universitas bina sarana informatika2 http://www.nusamandiri.ac.id1.3, http://www.bsi.ac.id2 e-mail : adeayu.aar@gmail.com1, tati.ttm@bsi.ac.id2, laela@nusamandiri.ac.id3 abstrak— layanan dompet digital memberikan banyak kemudahan dan keuntungan kepada para penggunanya. namun, tidak semua pengguna layanan dompet digital memiliki opini yang positif terhadap layanan tersebut. oleh karena itu, perusahaan layanan transportasi online perlu melakukan analisis untuk mengetahui sentimen masyarakat terhadap produknya. metode naïve bayes classifier merupakan metode yang sederhana, cepat, berakurasi tinggi, dan mempunyai performa yang cukup baik untuk melakukan klasifikasi data. namun, metode naïve bayes classifier mengasumsikan atributnya indepensi sehingga dapat menyebabkan akurasinya kurang optimal. tujuan penelitian ini adalah mengoptimalkan metode naïve bayes classifier menggunakan particle swarm optimization dalam klasifikasi polaritas percakapan layanan dompet digital. penelitian ini menggunakan data yang dari twitter sebanyak 490 data tweet. hasil pengujian dengan confusion matrix dan kurva roc menunjukkan peningkatan akurasi metode naïve bayes classifier dompet digital dana dari 60.00% menjadi 91.67% dan dompet digital isaku dari 53.23% menjadi 85.00%. hasil uji t-test dan anova menunjukkan hasil pengujian pada kedua metode klasifikasi memiliki perbedaan yang nyata dalam nilai accuracy. kata kunci: dompet digital; twitter; analisis sentimen; naïve bayes classifier; particle swarm optimization. abstract— digital wallet services adequately provides many benefits to its users. however, not all users of digital wallet services obtain a positive opinion about the service. therefore, online transportation service companies need to carry out an analysis to determine general sentiment towards their products. the naïve bayes classifier method represents a method that is simple, fast, excellent accuracy and obtains a comparatively excellent performance for classifying data. however, the naïve bayes classifier method assumes that the attributes are independent so that it can cause the accuracy to obtain less than optimal. this study aims to improve the accuracy of the naive bayes classification for the classification of public opinion on digital wallet services using particle swarm optimization. this study manages data from twitter as much as 490 tweet data. the test results with confusion matrix and roc curves show an increase in the accuracy of the naïve bayes classifier method for the dana digital wallet from 60.00% to 91.67% and the isaku digital wallet from 53.23% to 85.00%. the results of the t-test and anova test show that the test results of both classification methods provide significant differences in the accuracy value. keywords: digital wallet; twitter; sentiment analysis; naïve bayes classifier; particle swarm optimization. introduction in recent years, the popularity of digital wallet services in indonesia has experienced significant growth. digital wallets represents electronic money that introduces people to easy, safe, and profitable cashless or non-cash payment methods (aaputra, didi rosiyadi, windu gata, & syepry maulana husain, 2019). based on bank indonesia data, there was an increase in the number of electronic money transactions including digital wallets at the end of 2019 soaring 79.3% to 5.2 billion compared to 2018 of 2.9 billion transactions. moreover, the total nominal value of electronic money transactions experienced a drastic increase of 208.5%, reaching145 trillion rupiahs. this figure has increased to 98 trillion rupiahs or almost three times compared to 2018 of 47 trillion rupiahs (budiansyah, 2020). as of april 2020, 49 e-money companies have received official licenses from bank indonesia, including banks, technology, and communication companies (indonesia, 2020). http://creativecommons.org/licenses/by-nc/4.0/ mailto:adeayu.aar@gmail.com1 mailto:tati.ttm@bsi.ac.id2 p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 2 the work is distributed under the creative commons attribution-noncommercial 4.0 international license not all digital wallet services acquire several active users. this occurs due to a lack of public trust in the security of these services, and they still consider this as something new. based on the research results of iprice group and app annie, the ten digital wallet applications that have most significant number of monthly active users in the second quarter of 2019 are gopay, ovo, dana, linkaja, jenius, go mobile, isaku, sakuku, doku, and paytren, while the most downloaded digital wallet applications in the second quarter of 2019 are gopay, ovo, dana, linkaja, isaku, jenius, go mobile, paytren, sakuku, and doku (devita, 2019). digital wallet services adequately provides many benefits and advantages to their users. however, not all users of digital wallet services obtain a positive opinion of the service. in this digital era, people can provide opinions about a service, product, politics, and other topics through social media like twitter (mahendrajaya, buntoro, & setyawan, 2019). the number of daily twitter users jumped up in the 3rd quarter of 2019, daily users on twitter increased by 17% to 145 million users. one of the countries experiencing the most massive growth in active daily twitter users in indonesia (clinten, 2019). the number of tweets sent to twitter is up to 500 million daily tweets and 200 billion tweets (maulana, 2016). companies need to do sentiment analysis to find out what the public thinks about their products or services (pertiwi, 2019). sentiment analysis can extract public opinion on certain topics, politics, products, or services contained in unstructured texts (saidah & mayary, 2020). the previous research related to the analysis of the sentiment of digital wallet service users, namely research conducted by mahendrajaya, buntoro, and setyawan using the lexicon based and support vector machine methods. the sentiment labeling of gopay user comments from twitter is 923 positive comments and 287 negative comments. the sentiment labeling implements the lexicon based method. this study implements the svm method for classification of comparing two kernels. the linear kernel classification of comments as many as 1109 reviews got an accuracy value of 89.17% of the results. while the polynomial kernel with a comment classification of 1021 reviews got an accuracy value of 84.38%. the results of this study concluded that the classification of tweet data on twitter for gopay user comment reviews using the svm method and linear kernel is good (mahendrajaya et al., 2019). based on the description above, the researchers researched analyzing the sentiment of users of the dana and isaku digital wallet services, because not many have researched these digital wallets. we humbly propose implementing particle swarm optimization to improve the naïve bayes classifier method in the classification of public opinion on digital wallet services. this study aims to increase the accuracy value and auc value in the sentiment analysis of digital wallet service users by adding attribute weights using pso to the naïve bayes classifier method. materials and methods the stages carried out in this study used the cross standard industry process for data mining or crisp-dm methodology, as follows (pratama, pradnyana, & arthana, 2020): 1. business understanding business understanding is a stage in recognizing a business process in a company or organization in the form of business objectives, assessing conditions and field problems, and their needs. in this case, the business objectives being carried out are to find out the opinions given by users of the digital wallet services dana and isaku and apply the naïve bayes classifier and pso methods to analyze the sentiment of digital wallet service users. 2. data understanding data understanding is the stage of collecting data, understanding data, and identifying problems related to data quality. this study manages tweet data in indonesian from 19 june 2020 to 27 june 2020. the data collection process is by crawling tweet data from social media twitter using the twitter search operator on rapid miner 9.1. the keywords used are @danawallet and isaku. the data was taken from 19 june 2020 to 27 june 2020. from the results of the crawling, the data obtained were 490 tweets consisting of 272 tweet keywords @danawallet and 218 tweets with isaku keyword. 3. data preparation data preparation is the stage of preparing data for the next data mining process by changing the data from unstructured text documents to structured data. the application of data preparation in analyzing the sentiment of users of the dana and isaku has several stages, including (kurniawan & susanto, 2019): a. transform case the process of changing all capital letters into lowercase letters contained in tweet data so that they are uniform. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 3 the work is distributed under the creative commons attribution-noncommercial 4.0 international license b. tokenize the process of tokenization is to cut sentences into sections or words based on punctuation such as commas, periods, and other punctuation as needed. c. stopword removal this process stop removal is to eliminate unnecessary words. omitting the word will not change the information in it. d. stemming the process stemming is to remove the affixes contained in words so that all words return to their root words. 4. modeling modeling is the stage of processing data from preparation results to obtain the required information. this processing process uses the naive bayes classifier method to predict the probability of class membership and the addition of attribute weighting (attribute weighting) using pso to increase accuracy in the classification of the naïve bayes classifier. testing the proposed classification model uses the rapidminer 9.1 application. we tested the classification model that was formed to measure the level of accuracy and auc with randomly separated data with k-folds cross validation with k = 10. measurement of accuracy using confusion matrix and auc values using the roc curve. 5. evaluation evaluation is to validate the formed model. this evaluation uses a confusion matrix and roc curve and tests the significant difference between the weighting before and after weighting the attributes with pso on the naïve bayes classifier using the t-test and anova methods. figure 1. proposed model results and discussion this chapter will explain the results and discussion of the research on the sentiment analysis of digital wallet service users. 1. business understanding in this study, the business objectives carried out were to determine the opinions given by users of dana and isaku digital wallet services, apply the naïve bayes classifier and pso methods to analyze the sentiment of digital wallet service users, and find out the increase in the value of accuracy and auc value in sentiment analysis users of digital wallet services with additional weight attributes use pso to the naïve bayes classifier method. 2. data understanding data understanding of the data collection stage in this study is to retrieve tweet data with the crawling method from twitter social media using the twitter search operator on rapid miner 9.1 and enter the data in the form of ms. excel to facilitate data processing. the data taken is only tweets in indonesian. the keywords used are @danawallet and isaku . the data was taken from 19 june 2020 to 27 june 2020. from the results of the crawling, the data obtained were 490 tweets consisting of 272 tweet keywords @danawallet and 218 tweets with isaku keyword. the design of the tweet data crawling model is presented in figure 2. figure 2. tweet data crawling model design the flow of the data collection process in figure 2 is to search for tweet data on twitter based on the entered keywords. the use of this keyword as a sentiment analysis dataset, removes duplicates from the dataset based on the specified attributes. the attribute in this research is text. duplicate text represent the selected attribute has the same value in it. select the attributes you want to display and delete other attributes and convert the obtained dataset into ms file. excel. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 4 the work is distributed under the creative commons attribution-noncommercial 4.0 international license 3. data preparation (initial data processing) the data from the crawling that has been previously obtained is still raw data, where the data still contains a lot of noise and is unstructured. therefore, a preprocessing stage is needed to remove noise in words and data to make it more structured to facilitate research. preprocessing in this study uses the gataframework which can be accessed through http://www.gataframework.com/textmining.gataf ra-mework is an alternative in the pre-processing text to process words in indonesian because in the rapidminer application the dictionary to change indonesian acronyms and stopwords are still not available (hermanto, mustopa, & kuntoro, 2020). data from preprocessing results using gataframework will be used as a dataset for testing models in the rapidminer application. figure 3. display of gataframework text mining tools 4. modeling after carrying out the preprocessing stage, the next step is the classification process modeling process to determine a sentence as a member of the positive class or negative class based on the probability calculation value of the naïve bayes classifier formula. if the probability value in a sentence having a positive class is greater than the negative class, then the sentence is included in the positive class. and if the probability of the sentence having a positive class is smaller than the negative class, then the sentence is included in the negative class. the overall results of the classification data can be seen in table 1. table 1. amount of data class positive and negative digital wallets no digital wallets positive negative 1. dana 152 120 2. isaku 104 114 5. evaluation evaluation is done to validate the formed model. evaluation is done by using the confusion matrix and roc curve and testing the significant difference between before and after weighting the attributes with pso in the naïve bayes classifier using the t-test and anova methods. the results of the t-test and anova tests obtained a significant and more accurate model. a. testing the fund sentiment model using the naive bayes classifier the first experiment was to test the classification model using the naive bayes classifier method. the test design of the fund sentiment classification model using the naive bayes classifier method is presented in figure 4. figure 4. design of sentiment classification model funds using the naïve bayes classifier http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 5 the work is distributed under the creative commons attribution-noncommercial 4.0 international license in table 2, it is explained that the results of testing the 10 fold cross-validation model of dana's sentiment were obtained as many as 272 data consisting of 152 positive data and 120 negative data. a total of 88 data were predicted to be class positive according to the positive class prediction and 64 data predicted class positive turned out to be in the negative class, 75 data were predicted to be class negative accordingly, namely included in the negative class prediction and as many as 45 data predicted to be class negative turns into a positive class. the results obtained by using the naïve bayes classifier algorithm using rapid miner 9.1 get the accuracy value = 60.00% and auc = 0.599. table 2. results of the confusion matrix fund sentiment using the naïve bayes classifier accuracy : 60.00% +/11.53% (micro: 59.93%) true positive true negative class precision pred. positive 88 45 66.17% pred. negative 64 75 53.96% class recall 57.89% 62.50% figure 5. roc fund sentiment curve using the naïve bayes classifier b. sentiment model testing isaku uses the naive bayes classifier the first experiment was to test the classification model using the naive bayes classifier method. the test design of the sentiment classification model isaku using the naive bayes classifier method is presented in figure 6. figure 6. design of sentiment classification model isaku uses the naïve bayes classifier in table 3, it is explained that the test results of the model 10 fold cross-validation sentiment isaku obtained as many as 218 data consisting of 104 positive data and 114 negative data. a total of 30 data were predicted to be class negative according to the class negative prediction, and 84 data predicted class negative turned out to be in a positive class, 86 data were predicted to be class positive according to the class positive prediction, and 18 data predicted class positive turned out to be in the class positive. negative. the results obtained by using the naïve bayes classifier algorithm using rapid miner 9.1 get the accuracy value = 53.23% and auc = 0.520. table 3. results of confusion matrix sentiment isaku uses the naïve bayes classifier accuracy : 53.23% +/5.51% (micro: 53.21%) true negative true positive class precision pred. negative 30 18 62.50% pred. positive 84 86 50.59% class recall 26.32% 82.69% figure 7. roc sentiment curve isaku using the naïve bayes classifier http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 6 the work is distributed under the creative commons attribution-noncommercial 4.0 international license c. testing the fund sentiment model using the naive bayes classifier and pso the second experiment was to test the classification model using the naive bayes classifier and pso methods. the test design of the fund sentiment classification model using the naive bayes classifier and pso methods is presented in figure 8. figure 8. design of a fund sentiment model using nbc + pso based on the results of trials changing the value of inertia weight on the pso, the highest accuracy and auc values are located at population size 7, the maximum number of generation value is 100, and the inertia weight value 0.2 produces an accuracy value of 91.67% and an auc value of 0.750. table 4 explains that from a sample of 0.1 used in the classification with the naïve bayes classifier and pso, 14 of the fund's digital wallet service users were predicted to be class positive, which was included in the positive class prediction and 1 data predicted class positive turned out to be in the negative class, 11 the data predicted in the negative class was by the negative class prediction, and 1 data predicted the negative class turned out to be in a positive class. the results obtained by using the naïve bayes classifier algorithm and pso using rapid miner 9.1 get an accuracy value = 91.67% and auc = 0.750. table 4. funds sentiment confusion matrix results using nbc + pso accuracy : 91.67% +/-17.08 % (micro: 92.59 %) true positive true negative class precision pred. positive 14 1 93.33% pred. negative 1 11 91.67% class recall 93.33% 91.67% figure 9. roc fund sentiment curve using nbc + pso d. sentiment model testing isaku uses the naive bayes classifier and pso the second experiment was to test the classification model using the naive bayes classifier and pso methods. the test design of the sentiment classification model isaku using the naive bayes classifier and pso methods is presented in figure 10. figure 10. design of sentiment model isaku uses nbc + pso based on the results of trials changing the inertia weight value on the pso, the highest accuracy and auc values are located at population size 7, the maximum number of generation value is 100, and the inertia weight value 0.1 results in an accuracy value of 85.00% and an auc value of 0.800. table 5 explains from a sample of 0.1 which is used in the classification with the naïve bayes classifier and pso users of the digital wallet service i. as much as 8 data is predicted to be a negative class according to that is included in the negative class prediction and 3 data predicted the negative class turns into the positive class, 10 the data was predicted to be class positive according to the positive class prediction, and as many as 0 data was predicted to be class positive, it turned out to http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 7 the work is distributed under the creative commons attribution-noncommercial 4.0 international license be in the negative class. the results obtained by using the naïve bayes classifier algorithm and pso using rapid miner 9.1 get an accuracy value = 85.00% and auc = 0.800. table 5. results of confusion matrix sentiment isaku use nbc + pso accuracy : 85.00% +/22.91% (micro: 85.71%) true negative true positive class precision pred. negative 8 0 100.00% pred. positive 3 10 76.92% class recall 72.73% 100.00% figure 11. roc sentiment curve isaku using nbc + pso based on the test results, an evaluation was carried out by observing the comparison of the accuracy and auc values of each method as presented in table 6. the evaluation results showed that the accuracy and auc values of nbc + pso were higher than single nbc. the use of pso for attribute weights can increase the accuracy of the naïve bayes classifier algorithm in analyzing the sentiment of digital wallet service users. table 6. comparison of experimental results using nbc and nbc + pso naïve bayes classifier naïve bayes classifier dan pso accura cy auc accurac y auc dana 60.00 % 0.599 91.67% 0.750 isaku 53.23 % 0.520 85.00% 0.800 further evaluation was carried out by researchers to test the validity of the classification model performance using the t-test and anova test. e. t-test and anova test for fund sentiment the t-test and anova test designs for fund sentiment on the rapidminer 9.1 application are presented in figure 12. figure 12. t-test model design and anova model classification of nbc with nbc + pso fund sentiment the results of the t-test are presented in table 7 shows that the nbc + pso method has a significant difference in value because it has a probability of <0.050, namely 0.000 on the naive bayes classifier method. table 7. t-test results of naïve bayes classification model with nbc + pso fund sentiment t-test significance a b c 0.607 +/ 0.094 0.917 +/ 0.171 0.607 +/ 0.094 0.000 0.917 +/ 0.171 the anova test results are presented in table 8 showing that dk between groups (comparison) = 1, dk in residuals (denominator) = 18, and alpha = 0.050. then the f table value is f0.050 (1.18) = 4.41. and f count = 25,245. the value of fcount> ftable = 25,245> 4.41, then the two classification methods tested have a significant difference in the accuracy value. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 8 the work is distributed under the creative commons attribution-noncommercial 4.0 international license table 8. anova test results for naïve bayes classification model with nbc + pso fund sentiment anova test source square sums df mean squares f prob between 0.480 1 0.480 25.245 0.000 residuals 0.342 18 0.019 total 0.823 19 the evaluation results show that nbc + pso is a fairly good combination of methods in classifying data. the use of pso for attribute weighting affects increasing the value of accuracy in analyzing the sentiment of users of dana's digital wallet services. f. t-test and anova test for sentiment isaku the t-test and anova test design for sentiment isaku in the rapidminer 9.1 application are presented in figure 13. figure 13. design of the t-test and anova model test for classification of nbc with nbc + pso sentiment isaku the results of the t-test are presented in table 9 shows that the nbc + pso method has a significant difference in value because it has a probability of <0.050, namely 0.000 on the naive bayes classifier method. table 9. t-test results for naïve bayes classification model with nbc + pso sentiment isaku t-test significance a b c 0.523 +/ 0.053 0.850 +/ 0.229 0.523 +/ 0.053 0.000 0.850 +/ 0.229 anova test results are presented in table 10 showing that dk between groups (comparison) = 1, dk in residual (denominator) = 18, and alpha = 0.050. then the f table value is f0.050 (1.18) = 4.41. and f count = 19,377. the value of fcount> ftable = 19,377> 4.41, then the two classification methods tested have a significant difference in the accuracy value. table 10 anova test results for naïve bayes classification model with nbc + pso sentiment isaku anova test source square sums df mean squares f prob betwee n 0.536 1 0.536 19. 377 0.000 residu als 0.497 18 0.028 total 1.033 19 the evaluation results show that nbc + pso is a fairly good combination of methods in classifying data. the use of pso for attribute weighting affects increasing the value of accuracy in the sentiment analysis of isaku digital wallet service users. it can also be ignored that the digital wallet that has the best service is dana because most of its users give a positive opinion on the digital wallet service. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 4 september 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 9 the work is distributed under the creative commons attribution-noncommercial 4.0 international license conclusion the results of the classification of 490 tweet data using the naive bayes classifier show that the dana digital wallet has 152 positive sentiments and 120 negative sentiments, as well as the isaku, has 104 positive sentiments and 114 negative sentiments. testing tweet data using pso can increase the accuracy value and the auc value. the increase was significant, previously the sentiment test using nbc only produced 60.00% and an auc value of 0.599 after adding the pso, the accuracy value was 91.67% and the auc value was 0.750, while for sentiment testing isaku using nbc only produced 53.23% and a value auc 0.520 after adding the pso accuracy value to 85.00% and 0.800 auc value. weighting the attributes using pso has a major effect on the accuracy results obtained, giving an increase of 31.67% for fund sentiment and 31.77% for sentiment isaku. the results of the t-test and anova test show that the two classification methods tested have significant differences in the accuracy value. nbc + pso is a fairly good combination of methods in classifying data. the use of pso for attribute weighting affects increasing the value of accuracy in analyzing the sentiment of users of the dana and isaku digital wallet services. reference aaputra, s. a., didi rosiyadi, windu gata, & syepry maulana husain. (2019). sentiment analysis analisis sentimen e-wallet pada google play menggunakan algoritma naive bayes berbasis particle swarm optimization. jurnal resti (rekayasa sistem dan teknologi informasi), 3(3), 377–382. https://doi.org/10.29207/resti.v3i3.1118 budiansyah, a. (2020). gopay & ovo cs kian populer, transaksi tembus rp 145 t. retrieved april 23, 2020, from cnbc indonesia website: https://www.cnbcindonesia.com/tech/2020 0204112543-37-135041/gopay-ovo-cs-kianpopuler-transaksi-tembus-rp-145-t clinten, b. (2019). pengguna aktif harian twitter indonesia diklaim terbanyak. retrieved april 24, 2020, from kompas website: https://tekno.kompas.com/read/2019/10/3 0/16062477/pengguna-aktif-harian-twitterindonesia-diklaim-terbanyak devita, v. d. (2019). siapa aplikasi e-wallet dengan pengguna terbanyak di indonesia? retrieved june 11, 2020, from iprice group website: https://iprice.co.id/trend/insights/e-walletterbaik-di-indonesia/ hermanto, h., mustopa, a., & kuntoro, a. y. (2020). algoritma klasifikasi naive bayes dan support vector machine dalam layanan komplain mahasiswa. jitk (jurnal ilmu pengetahuan dan teknologi komputer), 5(2), 211–220. https://doi.org/10.33480/jitk.v5i2.1181 indonesia, b. (2020). informasi perizinan penyelenggara dan pendukung jasa sistem pembayaran. retrieved april 23, 2020, from bank indonesia website: https://www.bi.go.id/id/sistempembayaran/informasi-perizinan/uangelektronik/penyelenggaraberizin/contents/default.aspx kurniawan, i., & susanto, a. (2019). implementasi metode k-means dan naïve bayes classifier untuk analisis sentimen pemilihan presiden (pilpres) 2019. eksplora informatika, 9(1), 1– 10. https://doi.org/10.30864/eksplora.v9i1.237 mahendrajaya, r., buntoro, g. a., & setyawan, m. b. (2019). analisis sentimen pengguna gopay menggunakan metode lexicon based dan support vector machine. komputek, 3(2), 52. https://doi.org/10.24269/jkt.v3i2.270 maulana, a. (2016). twitter rahasiakan jumlah pengguna di indonesia. retrieved april 24, 2020, from cnn indonesia website: https://www.cnnindonesia.com/teknologi/2 0160322085045-185-118939/twitterrahasiakan-jumlah-pengguna-di-indonesia pertiwi, m. w. (2019). analisis sentimen opini publik mengenai sarana dan transportasi mudik tahun 2019 pada twitter menggunakan algoritma naïve bayes, neural network, knn dan svm. inti nusa mandiri, 14(1), 27–32. pratama, k. a., pradnyana, g. a., & arthana, i. k. r. (2020). pengembangan sistem cerdas untuk prediksi daftar kembali mahasiswa baru dengan metode naive bayes (studi kasus: universitas pendidikan ganesha). sintech journal, 3(1), 22–34. saidah, s., & mayary, j. (2020). analisis sentimen pengguna twitter terhadap dompet http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v2i4.162 jurnal riset informatika vol. 2, no. 4 september 2020 10 the work is distributed under the creative commons attribution-noncommercial 4.0 international license elektronik dengan metode lexicon based dan k – nearest neighbor. jurnal ilmiah informatika komputer, 25(1). http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 17 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional penerapan transformasi data discrete wavelet transform pada neural network untuk prediksi harga saham indah suryani teknik informatika stmik nusa mandiri jakarta indah.ihy@nusamandiri.ac.id abstrak penelitian mengenai harga saham memang masih menarik bagi para peneliti. seperti halnya dalam penelitian ini, data penutupan harga saham antm dijadikan sebagai set data yang diolah untuk kemudian dilakukan prediksi harga kedepannya. adapun metode neural network merupakan metode yang sangat banyak digunakan peneliti karena berbagai keunggulannya. sedangkan metode discrete wavelet transform digunakan untuk melakukan transformasi data. penggunaan transformasi data menggunakan discrete wavelet transform diharapkan dapat meningkatkan kualitas data sehingga dapat meningkatkan performa neural network. adapun berdasarkan eksperimen yang dilakukan dengan metode neural network dengan fungsi aktivasi binary sigmoid menunjukkan hasil rmse 0,024 sampai dengan 0,022. sedangkan dari hasil eksperimen neural network dengan fungsi aktivasi binary sigmoid yang dilakukan transformasi data dengan discrete wavelet transform, telah menghasilkan rmse yang lebih kecil daripada eksperimen prediksi yang tanpa menggunakan transformasi data dengan discrete wavelet transform yaitu 0,02 sampai dengan 0,018. dari hasil perbandingan rmse tersebut, terdapat selisih nilai rata-rata rmse sebesar 0,0039. artinya penerapan transformasi data menggunakan discrete wavelet transform ini ternyata mampu meningkatkan performa prediksi dengan neural network yaitu dengan menghasilkan nilai error yang lebih kecil atau menghasilkan prediksi yang lebih akurat. kata kunci: prediksi, harga saham, neural network, discrete wavelet transform abstract research on stock prices is still interesting for researchers. as in this study, antm's stock price closing data is used as a data set that is processed and then predicted in the future. the neural network method is a method that is very widely used by researchers because of its various advantages. while the discrete wavelet transform method is used to perform data transformation. the use of data transformation using discrete wavelet transform is expected to improve data quality so that it can improve neural network performance. the experiment based on the neural network method with the binary sigmoid activation function shows the results of rmse from 0.024 to 0.022. while the results of neural network experiments with the binary sigmoid activation function which carried out data transformation with discrete wavelet transform, has produced a smaller rmse than prediction experiments without using data transformation with discrete wavelet transform that is 0.02 to 0.018. from the results of the rmse comparison this, there is a difference in the average value of rmse of 0.0039. this means that the application of data transformation using discrete wavelet transform turns out to be able to improve the performance of predictions with neural networks by producing smaller error values or producing more accurate predictions. keywords: prediction, stock prices, neural network, discrete wavelet transform pendahuluan prediksi pasar saham selalu menjadi hal yang menarik bagi para peneliti (rajput & bobde, 2016). sejalan dengan pendapat (a, adebiyi, k, charles, o, marion, & o, sunday, 2012) bahwa prediksi harga saham dengan teknik datamining adalah salah satu masalah terpenting dalam keuangan yang diselidiki oleh para peneliti di seluruh dunia. data harga saham merupakan data kuantitatif yang termasuk ke dalam data time series. time series merupakan satu set pengamatan kuantitatif yang diatur dalam urutan kronologis (kirchgässner & wolters, 2007). time series plots dapat mengungkapkan pola seperti random, tren, pergeseran tingkat, periode atau siklus, pengamatan yang tidak biasa atau kombinasi dari pola (montgomery, 2008). http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 18 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional dalam berbagai bidang penelitian, metode neural network merupakan salah satu metode yang paling banyak digunakan oleh para peneliti. manfaat utama dari penggunaan neural network (bennett, stewart, & lu, 2014) adalah kemampuannya untuk menggeneralisasi, mengidentifikasi hubungan non-linear dan penerapan ke berbagai aplikasi. sebagai approximators dan sistem pembelajaran yang fleksibel, jaringan saraf telah menarik meningkatnya minat dalam menggunakan mereka untuk pemodelan dan peramalan runtun waktu (ouyang & yin, 2014). discrete wavelet transform mirip dengan discrete fourier transform dan banyak digunakan dalam aplikasi praktis. prinsipnya tetap sama dengan transformasi lainnya. sinyal diubah menjadi bentuk yang berbeda menggunakan fungsi dasar yang lebih cocok untuk pemrosesan yang diperlukan, dan transformasi dapat dilakukan secara efisien menggunakan algoritma cepat (sundararajan, 2015). haar discrete wavelet transform adalah wavelet paling sederhana diantara berbagai jenis wavelet. beberapa penelitian terkait dengan topik yang diangkat dalam penelitian ini diantaranya adalah penelitian yang dilakukan oleh (a, adebiyi et al., 2012) yang menyajikan pendekatan hibdrida dari kombinasi variabel terhadap analisis teknis dan analisis fundamental untuk membuat model prediksi feed forward multilayer perceptrom neural network yang dilatih menggunakan algoritma backpropagation untuk meningkatkan akurasi prediksi harga saham. pada hasil empirisnya menunjukkan level akurasi tinggi untuk prediksi harga saham menggunakan pendekatan hibrida ternyata lebih baik dari pendekatan analisis teknis. dalam penelitiannya (anbazhagan & kumarappan, 2014) mengangkat mengenai perlunya proses pra pengolahan data untuk mengekstrak informasi berlebihan dari sinyal asli. dalam penelitiannya dilakukan proses pra pengolahan data dengan menggunakan metode discrete cosine transform untuk meningkatkan efisiensi pembelajaran pada feed forward neural network. hasilnya menunjukan bahwa model ini menunjukkan kompleksitas dan waktu komputasi yang lebih rendah jika dibandingkan dengan 17 model lainnya. selain itu penelitian (suryani, 2015) juga menunjukkan peningkatan terhadap evaluasi nilai root mean square error (rmse) terhadap prediksi harga emas dengan menggunakan metode neural network yang sebelumnya dilakukan transformasi data menggunakan exponential smoothing. salah satu keterbatasan metode penelitian adalah bahwa mereka mengabaikan potensi transformasi untuk meningkatkan perkiraan (beaumont, 2014). maka berdasarkan hasil penelitian terkait, pada penelitian ini dilakukan penerapan transformasi data menggunakan discrete wavelet transform yang diharapkan dapat meningkatkan performa dari metode neural network dalam melakukan prediksi harga saham antm. metode penelitian jenis penelitian penelitian ini meerupakan penelitian kuantitatif berupa penelitian eksperimental. data dan teknik pengumpulan data data yang digunakan dalam penelitian ini adalah data saham perusahaan aneka tambang persero, tbk. data tersebut berupa data historis harga saham antm yang dikumpulkan dari data sekunder yang diambil dari situs web. data saham antm yang digunakan dalam penelitian ini berupa data saham antm sebanyak 2.699 record dari 02 januari 2008 hingga 28 desember 2018. dari data tersebut dipilih entitas berupa tanggal dan harga penutupan saham yang kemudian digunakan dan diolah dalam penelitian ini. data harga saham antm tersebut dapat dilihat pada tabel 1. tabel1. sample data harga saham antm date close 28/12/2018 765 27/12/2018 770 26/12/2018 770 21/12/2018 770 20/12/2018 765 19/12/2018 760 18/12/2018 750 17/12/2018 730 14/12/2018 755 13/12/2018 765 12/12/2018 755 11/12/2018 755 10/12/2018 720 07/12/2018 725 06/12/2018 735 05/12/2018 740 04/12/2018 710 03/12/2018 735 30/11/2018 615 29/11/2018 625 15/11/2018 670 http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 19 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional teknik analisis data dari data yang telah dikumpulkan tersebut, kemudian dilakukan proses pengolahan data awal berupa tahapan pra pengolahan data. adapun tahapan pra pengolahan data awal yang dilakukan dalam penelitian ini meliputi: 1. replace missing value pada penelitian ini, pada pengolahan data awal yang pertama kali dilakukan adalah dengan melakukan replace missing value dikarenakan terdapat data yang masih missing value . (hofmann, 2009) replace missing value yaitu salah satu operator yang terdapat di data cleansing pada rapidminer yang membantu menangani nilai null yang mungkin ada dalam data, yang dapat digunakan untuk menemukan nilai-nilai yang hilang dalam atribut atau serangkaian atribut dan merubahnya, dari nilai yang hilang ke nilai yang diinginkan 2. set role pada penelitian ini, set role operator digunakan untuk menjadikan atribut date sebagai atribut spesial yaitu sebagai atribut id 3. normalize windowing merupakan salah satu teknik dalam menentukan data input dan data output dalam prediksi data runtun waktu dengan tipe univariat. data univariat adalah distribusi data dengan melibatkan satu atribut atau variabel (han, kamber, & pei, 2012). pada penelitian ini dilakukan normalisasi data menggunakan fungsi aktivasi binary sigmoid dengan jangkauan 0,1 s/d 0,9. perhitungan untuk binary sigmoid (logsig) didapat dari rumus sebagai berikut: 𝑦′ = 𝑥−𝑥𝑚𝑖𝑛 𝑥𝑚𝑎𝑥−𝑥𝑚𝑖𝑛 × (0.9 − 0.1) + 0.1 .............. ... (1) adapun ilustrasi dari fungsi binary sigmoid dapat dilihat pada gambar 1 berikut. f(x) 0 1 gambar 1. fungsi binary sigmoid 4. windowing teknik windowing dilakukan untuk memecah atribut close pada data harga saham untuk kemudian dipecah menjadi 5 data input dan 1 data output. data input merupakan data 5 hari sebelumnya dan data output adalah data 1 hari berikutnya 5. discrete wavelet transform transformasi data dilakukan dengan mengaplikasikan operator process series yang kemudian dipilih metode tranformasi data dengan discrete wavelet transform berupa haar wavelet. kemudian dari pengolahan data tersebut menghasilkan set data baru dan kemudian diolah dengan metode neural network menggunakan 10 fold cross validation yang dipecah dalam data training dan data testing. kemudian akan didapat nilai rmsenya untuk kemudian dilakukan perbandingan antara metode neural network dengan metode yang diusulkan yaitu metode neural netwotk yang ditambahkan transformasi data dengan discrete wavelet transform. adapun prosesnya dapat dilihat pada gambar 2 sebagai berikut. set data replace missing value set role normalize windowing discrete wavelet transform set data baru perbandingan rmse pra pengolahan data process series x validation neural network data pelatihan rmse data pengujian model evaluasi gambar 2. metode yang diusulkan http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 20 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional hasil penelitian dan pembahasan pada penelitian ini, eksperimen yang dilakukan menggunakan tools rapidminer 8.0. tahapan eksperimen yang dilakukan adalah sebagai berikut: 1. menyiapkan set data yang digunakan yaitu berupa data saham antm sebanyak 2.669 record 2. melakukan proses pra pengolahan data dengan melakukan replace missing value, set role, normalize dan windowing 3. melakukan transformasi data menggunakan process series dengan discrete wavelet transform menggunakan haar wavelet dan memilih forward direction 4. menerapkan metode neural network dengan memasukan parameter berupa training cycle, learning rate, momentum dan hidden layer 5. melakukan training dan testing terhadap metode usulan 6. melakukan evaluasi dengan mencatat hasil rmse dari eksperimen yang telah dilakukan. adapun perhitungan hasil rmse didapat dari rumus berikut. 𝐴 = √ ∑ (𝐺𝑖−𝐺𝑖′)𝑁𝑖=1 𝑁 .............. .......................................(2) eksperimen pertama dilakukan dengan melakukan inisialisasi parameter neural network yang terdiri dari training cycle, learning rate, momentum dan hidden layer dan normalisasi neural network menggunakan fungsi aktivasi logsig atau binary sigmoid berupa jangkauan 0,1 sampai dengan -0,9. hasil eksperimen ini kemudian dicatat ke dalam tabel 2 berikut ini. tabel 2. hasil eksperimen metode neural network (fungsi aktivasi binary sigmoid) no perco baan hidd en layer size train ing cycle learn ing rate mom entu m ho riz on rmse 1 1 500 0.3 0.2 1 0,022 2 1 500 0.6 0.3 1 0,023 3 3 1000 0.6 0.3 1 0,023 4 3 1000 0.9 0.6 1 0,023 5 3 500 0.9 0.6 1 0,023 6 1 300 0.5 0.5 1 0,023 7 1 300 0.1 0.3 1 0,024 8 3 500 0.3 0.2 1 0,022 9 3 500 0.6 0.3 1 0,023 10 3 500 0.9 0.6 1 0,023 eksperimen selanjutnya dilakukan dengan menerapkan metode usulan berupa penerapan transformasi data discrete wavelet transform dengan memilih metode haar dan forward direction untuk transformasi discrete wavelet transform nya. selanjutnya menginisialisasi parameter neural network yang terdiri dari training cycle, learning rate, momentum dan hidden layer dan normalisasi neural network menggunakan fungsi aktivasi logsig atau binary sigmoid berupa jangkauan 0,1 sampai dengan -0,9. hasil eksperimen ini kemudian dicatat ke dalam tabel 3 sebagai berikut. tabel 3. hasil eksperimen metode neural network (fungsi aktivasi binary sigmoid)+discrete wavelet transform no perc obaa n hidd en layer size train ing cycle lear ning rate mom entu m horiz on rmse 1 1 500 0.3 0.2 1 0,019 2 1 500 0.6 0.3 1 0,018 3 3 1000 0.6 0.3 1 0,018 4 3 1000 0.9 0.6 1 0,019 5 3 500 0.9 0.6 1 0,02 6 1 300 0.5 0.5 1 0,018 7 1 300 0.1 0.3 1 0,02 8 3 500 0.3 0.2 1 0,02 9 3 500 0.6 0.3 1 0,018 10 3 500 0.9 0.6 1 0,02 gambar 3 di bawah ini merupakan arsitektur eksperimen prediksi harga saham menggunakan metode neural network dengan transformasi data discrete wavelet transform dengan parameter 1 hidden layer, training cycle 300, dan learning rate dan momentum masingmasing 0,5 yang menghasilkan rmse sebesar 0,018.. gambar 3. arsitektur neural network + discrete wavelet transform http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 21 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional dari eksperimen metode neural network dan neural network discrete wavelet transform, terdapat beberapa perbedaan hasil rmse yang kemudian dilakukan pencatatan hasil rmsenya ke dalam tabel 4 sebagai berikut. tabel 4. perbandingan hasil rmse nn dan nn+dwt neural network neural network + dwt 0,022 0,019 0,023 0,018 0,023 0,018 0,023 0,019 0,023 0,02 0,023 0,018 0,024 0,02 0,022 0,02 0,023 0,018 0,023 0,02 berdasarkan data pada tabel 3 di atas, maka dapat digambarkan dalam gambar 4 di bawah ini bagaimana selisih dari perbandingan hasil rmse dari kedua eksperimen tersebut. gambar 4. grafik perbandingan rmse neural network (fungsi aktivasi binary sigmoid dan neural network (fungsi aktivasi binary sigmoid)+ discrete wavelet transform simpulan dan saran simpulan metode usulan pada penelitian ini diterapkan dengan melakukan transformasi data discrete wavelet transform untuk mengembangkan metode neural network dengan fungsi aktivasi binary sigmoid. metode usulan ini digunakan untuk melakukan prediksi terhadap data saham antm yang kemudian berdasarkan eksperimen yang telah dilakukan terbukti dapat meningkatkan hasil prediksi harga saham. hal ini dilakukan dengan melihat perbandingan hasil rmse yang dihasilkan. pada eksperimen menggunakan metode neural network fungsi aktivasi binary sigmoid, dari 10 eksperimen yang dilakukan, menghasilkan nilai rmse terkecil sebesar 0,022 dan rmse rata-rata sebesar 0,0229. sedangkan untuk metode usulan yaitu metode neural network fungsi aktivasi binary sigmoid dengan transformasi data discrete wavelet transform dihasilkan rmse terkecil sebesar 0,018 dan rmse rata-rata sebesar 0,019 sehingga terdapat selisih nilai rmse sebesar 0,0039. saran berdasarkan kesimpulan penelitian, maka untuk penelitian di masa mendatang dapat dilakukan pengembangan terhadap metode neural network dengan metode lainnya untuk dapat lebih meningkatkan performa neural network sehingga menghasilkan prediksi yang lebih akurat lagi. daftar referensi a, adebiyi, a., k, charles, a., o, marion, a., & o, sunday, o. (2012). stock price prediction using neural network with hybridized market indicators. journal of emerging trends in computing and information sciences, 3(1), 1–9. anbazhagan, s., & kumarappan, n. (2014). dayahead deregulated electricity market price forecasting using neural network input featured by dct. energy conversion and management, 78, 711–719. https://doi.org/10.1016/j.enconman.2013.1 1.031 beaumont, a. n. (2014). data transforms with exponential smoothing methods of forecasting. international journal of forecasting, 30(4), 918–927. https://doi.org/10.1016/j.ijforecast.2014.03. 013 bennett, c. j., stewart, r. a., & lu, j. w. (2014). forecasting low voltage distribution network demand profiles using a pattern recognition based expert system. energy, 67, 200–212. https://doi.org/10.1016/j.energy.2014.01.0 32 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 22 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional han, j., kamber, m., & pei, j. (2012). data mining: concepts and techniques. hofmann, m. (2009). data mining and knowledge discovery series. kirchgässner, g., & wolters, j. (2007). introduction to modern time series analysis. https://doi.org/10.1007/978-3-540-732914 montgomery, d. c. (2008). introduction to time series analysis and forecasting. ouyang, y., & yin, h. (2014). a neural gas mixture autoregressive network for modelling and forecasting fx time series. neurocomputing, 135, 171–179. https://doi.org/10.1016/j.neucom.2013.12.0 37 rajput, v., & bobde, s. (2016). stock market forecasting techniques: literature survey. international journal of computer science and mobile computing, 5(6), 500–506. retrieved from www.ijcsmc.com sundararajan, d. (2015). discrete wavelet transform: a signal processing approach. in discrete wavelet transform: a signal processing approach. https://doi.org/10.1002/9781119113119 suryani, i. (2015). penerapan exponential smoothing untuk transformasi data dalam meningkatkan akurasi neural network pada prediksi harga emas. 1(2). http://creativecommons.org/licenses/by-nc/4.0/ 119 pakpak language translator application into indonesian using algorithmboyer moore based on android khairani purba1, charles jhony mantho sianturi2*), mikha dayan sinaga3, nita sari sembiring4, erwing ginting5, muhammad fauzi6 1,2,3,4,5,6jurusan teknik informatika universitas potensi utama https://potensi-utama.ac.id/ khairani0610@gmail.com1,79sianturi@gmail.com2, mikhadayan88@gmail.com3, nita.sembiring86@gmail.com4,erwinginting82@gmail.com 5, mfauzixx@gmail.com6 abstrak minimnya pelestarian juga pengetahuan mengenai bahasa pakpak di indonesia yang menyebabkan bahasa pakpak kelestariannya kurang terjaga terutama bagi para kalangan muda yang terus mengikuti perkembangan zaman. hal ini menyebabkan proses globalisasi dan urbanisasi yang menyebabkan terjadinya asimilasi dan akulturasi budaya, khususnya daerah perkotaan. keadaan ini memicu bahasa baru yang sangat disukai terutama bagi kalangan muda yang tanpa disadari hal tersebut membuat kita kehilangan identitas sebagai masyarakat yang memiliki suku dan adat istiadat masing – masing dan munculnya sekolah internasional dan nasional yang mengharuskan siswanya berbahasa asing. sebab itu, dibutuhkannya pembelajaran untuk menjaga kelestarian bahasa pakpak. dengan cara membuat aplikasi penerjemah bahasa pakpak ke bahasa indonesia yang memakai algoritma boyer moore berbasis android. aplikasi penerjemah ini dibuat untuk pengenalan bahasa pakpak untuk masyarakat luas sehingga membuat bahasa pakpak kelestariannya tetap terjaga dan aplikasi penerjemah ini bias menerjemahkan bahasa pakpak ke bahasa indonesia atau sebaliknya yang berdasarkan kamus pakpak – indonesia yang berlaku. kata kunci: bahasa pakpak, bahasa indonesia, algoritma boyer moore, android abstract the lack of preservation is also the knowledge of the pakpak language in indonesia, which causes the pakpak language to be less preserved, especially for young people who continue to keep abreast of the times. this causes the process of globalization and urbanization which causes assimilation and acculturation, especially in urban areas. this situation triggers a new language that is very popular, especially for young people who unconsciously, it makes us lose our identity as a society that has tribes and customs each – and the emergence of international and national schools that require students to speak foreign languages. therefore, learning is needed to preserve pakpak language. by making a pakpak to indonesian translator application that uses the android based boyer moore algorithm. this translator application was made for the introduction of the pakpaklangugae to the wider community so that the sustainability of the pakpak language is maintained and this translator application can translate the pakpak language into indonesian or vice versa based on the prevailing pakpak – indonesian dictionary. keywords: pakpak language, indonesian, boyer moore's algorithm, android introduction regional languages are a means of communication for every ethnic/tribe in indonesia. regional languages are rarely used as a means of communication when they are overseas, especially the pakpak language. given that the pakpak language has begun to be abandoned, where most of the younger generation are less aware of the importance of regional languages. the pakpak language translator application into indonesian is designed to translate words and sentences where this application has 2 features, namely pakpak indonesian and indonesian pakpak by applying the boyer moore algorithm. with this application, it can help in the communication process between anyone who does not understand the pakpak language and introduces regional languages, especially the pakpak language. as a type of art, literature has existed in the course of human civilization. the process of education, introduction, and understanding of 120 literature will be able to enrich humans as individuals in continuous dialogue with the human world and humanity. in this context, literature has the potential as a transmitter of various values and can be a source of inspiration about virtue and wisdom (sukirman, 2021). regional languages also have an important role in shaping human character. regional languages are part of a culture that lives and develops according to the needs of the community. however, in this era of globalization, there is concern from language observers that many regional languages are threatened with extinction. this anxiety deserves attention because the loss of a regional language is an indication of the loss of world culture and civilization (nikmatuzaroh, 2018). the phenomenon of the extinction of regional languages in indonesia seems to have become a problem that has attracted the attention of many scientists, especially linguists. various efforts have been and are being made to save regional languages which tend to lead to the process of extinction. of course, it is quite reasonable considering that indonesia is a country that has the second most regional languages in the world after papua new guinea(tondo, 2009). the division (read: division) of dairi regency into two regencies is a political decision (action) involving the pakpak ethnic group or the pakpak people. the political action that gave birth to west pakpak regency as a new division, and dairi regency as the parent regency, was confirmed by law of the republic of indonesia number 9 of 2003 concerning the establishment of south nias regency, pakpak bharat regency, and humbang hasundutan regency in north sumatra province. the expansion of dairi regency is inseparable from the official implementation in 2001 of law no. 22 of 1999 concerning regional government(zuska, 2013). in ida basaria's research, i want to examine the pragmatic functions of the pakpak dairi language (hereinafter referred to as bpd), so that it will be known whether bpd belongs to a language group that emphasizes a subject (subject prominent language) or a language group that highlights a topic (topic prominent language). the study is based on the theoretical framework of language typology about the difference between language that emphasizes the subject and language that emphasizes(basaria, 2014). regional languages are a valuable asset of a nation. however, the paradigm of 21st-century society views that foreign languages have higher prestige than national and regional languages. in other words, regional languages are the third priority in their use after national and foreign languages. the preservation of regional languages is one of the phenomena as well as steps that arise in the mindset of the polemic of a shift in regional languages(widianto, 2018). the government cannot maintain the regional language without the awareness of the speakers to maintain the regional language itself. the role and contribution of local language users itself greatly affect the success of local language defense(alimin & fajri, 2020). the translation is the process of transferring language, word by word from one language to another. another theory states that translation is an activity of replacing text/speech/speech material in the source language to equivalent text/speech/speech material into the target language. (priyanto & ulinnuha, 2017). research from muhammad zulham, helmi kurniawan, and iwan fitrianto rahmad entitled design of email data security applications using android-based rc6 encryption algorithm. the purpose of this study is to secure messages that will be encoded on email in data confidentiality and can send messages and receive messages through email intermediaries using the rc6 android application. (zulham et al., 2014). based on the research entitled "implementation of the salsa20 stream cipher cryptographic technique for database security". this study concludes that the salsa20 stream cipher cryptographic technique can be used to provide increased data security through the encryptiondecryption process before the data is stored in a database. cryptographic techniques with the stream cipher algorithm method can be applied to ensure the security of electronic document files. one that can be used is the encryption and decryption of text data or in other words, encoding the data so that only the intended person can know the contents of the data. (munandar et al., 2020). research conducted by asbon hendra and ratih adinda destari entitled expert system to identify ariston water heater damage using webbased backward chaining method. from the research conducted, it is stated that the application is built using the backward chaining method and several programming languages such as php, mysql and others. so it doesn't take long and gives a good impact(hendra & destari, 2015). research conducted by khairani puspita and m. rhifky wayahdi entitled analysis of the combination of ceaser cipher, vernam cipher and hill cipher methods in the cryptographic process. in this study caesar cipher, vernam cipher, hill cipher are classical cryptography. this method is very strong in security and has security that is very 121 difficult to break and can be modified and combined(puspita & wayahdi, 2015). the boyer-moore algorithm is a string search algorithm, published by robert s. boyer, and j. strother moore in 1977. this algorithm is considered the most efficient algorithm in general applications (argakusumah & hansun, 2014). unlike the string search algorithm found previously, the boyer-moore algorithm starts matching characters from the right of the pattern (the pattern you are looking for). (ramadhansyah, 2013). the idea behind this algorithm is that by starting character matching from the right, and not from the left, more information will be obtained (darmawan et al., 2018). boyer-moore algorithm is famous because it is widely applied to the matching algorithm for many strings (multiple patterns). the basic idea of the boyer-moore algorithm is as simple as the brute force algorithm by using the help of a table containing the steps for moving the pattern to the right when it encounters a character mismatch. (ardi et al., 2017). android is a subset of software for mobile devices that includes an operating system, middleware¸, and core applications released by google. android is a mobile operating system that adopts the linux operating system but has been modified(lengkong et al., 2015). the purpose of this research is to introduce and provide knowledge about the pakpak language, assist in communicating with people who use the pakpak tribal language, apply the boyer moore algorithm in translating pakpak language into indonesian, build an application that can translate pakpak language into indonesian using the boyer moore method, and building an application that can translate pakpak language into indonesian using the android-based boyer moore method. research methods data collection at this stage the author also collects data through: 1. field study this research is a direct study to see or review the location. data collection techniques are as follows: a) interviews, namely holding questions and answers to related sources. mr. drs. amhar kudadiri, m.hum who knows about pakpak culture and language and is the secretary of the literature study program, faculty of science and culture at the university of north sumatra. b) observations, namely by observing the pakpak people in north sumatra, especially in the medan city area. 2. literature study this stage is carried out to collect data on writing this thesis through articles, books, journals and others. design procedure this analysis is carried out to determine the stages of research completion, as shown in figure 1: pakpak language translator application into indonesian requirements analysis tools (hardware & software) data boyer moore algorithm computer unity vuforia android application uml design tool coding application testing testing method figure 1. fishbone diagram research research results and discussion 1. discussion a. boyer moore algorithm method boyer moore algorithm can be seen in the figure 2 flowchart as follows. figure 2 it can be seen the boyer moore process contained in the system to be built. first, enter the 122 pattern in the form of characters to be able to do a string search. then read the pattern on the text in sqlite, whether the searched string is a match in the text. performs string matching from right to left according to the input pattern desired by the user. start input pattern pattern identification in text database test string similarity from right to left no finding pattern in text yes finding meaning end figure 2. flowchart diagram of boyer moore algorithm this is done until the pattern you are looking for is matched. after doing the matching, the pattern will get a match on the available text. where there has been grouping of data to directly know the meaning. finally, the system issues an output, where the system automatically issues all options based on the inputted pattern and displays the translation results based on the search process using the boyer moore algorithm. b. system modeling 1) use case diagram use case diagrams are used to see a sequence of systems built and can see the related relationships. the use case diagram of the research can be seen in figure 3 below. pakpak language translator application into indonesian user insert word search for word using boyer moore algorithm result * * * * ** figure 3. use case diagram of the pakpak to indonesian translator application 2) activity diagram activity diagram is a process that explains the various related flows in the system that will be designed from the beginning to the end, it can be seen in figure 4: sistempengguna masukkan kata proses pencarian kata dengan algoritma boyer moore terjemahanhasil pencarian dan terjemahan ya tidak figure 4. activity diagram of the pakpak language translator application to indonesian sequence diagram sequence diagram displays the interaction between objects in the system built, can be seen in figure 5: translation page database insert word searching result _ _ _ _ _ _ figure 5. sequence diagram of the pakpak to indonesian translator application 2. results a. user interface these results are used to show the appearance of the pakpak language translator application into indonesian using the android-based boyer moore algorithm. the following will explain the display of the results of the pakpak language translator application into indonesian. 1) splash screen splash screen is the display that will appear the first time when we run the pakpak language translator application into indonesian based on android, it can be seen in figure 6: 123 figure 6. splash screen display 2) main page the main page of the application has several menu options such as the homepage, pakpak indonesian translator, pakpak indonesian translator, about and exit, can be seen in figure 7. figure 7. main page display 3) home when the home menu is clicked by the user, it will display information at a glance about a brief explanation of the translator application, which can be seen in figure 8: figure 8. home view 4) pakpak – indonesia this page shows that testing the boyer moore algorithm for translating pakpak language into indonesian can display perfect translation results as in the sqlite database, can be seen in figure 9: figure 9. pakpak display – indonesia 5) indonesia – pakpak this display shows that testing the boyer moore algorithm for translating indonesian into pakpak language can display perfect translation results such as those in the sqlite database, can be seen in figure 10: figure 10. indonesian display – pakpak 6) about this page contains the author's information briefly such as name, number, study program, address and email, you can see figure 11: 124 figure 11. display about c. testing this trial is carried out to find out the system designed is in good condition or condition or not and if it is in accordance with what was built it can be used, this application test is carried out using blackbox testing: table 1. application test plan tested results test items splash carry out the loading process to enter the main menu view home showing the meaning of translator pakpak – indonesia displays the pakpak – indonesian language translation process where words can be input and displays the translation results indonesia – pakpak displays the indonesian pakpak translation process where words can be input and display the translation results about showing about the author exit the process of exiting the application conclusions and suggestions conclusion from the discussion and trials that have been made, it can be concluded that the boyer moore algorithm can be used to complete the translation of words or sentences and this application system performs the process of translating words or sentences based on the vocabulary in the sqlite database in the application. this language translator application has been successfully built and can be used as a learning medium to make it easier for people to know the local language, namely pakpak language. suggestion in order to improve the designed application, suggestions are given, such as further development of the addition of copy, cut, text to speech, and other additional features, and in the translator application. pakpak language into indonesian so that it can be further developed in terms of adding information or information to the word you are looking for. to be able to use language more effectively on vocabulary. acknowledgments the author would like to thank the university of potential utama for giving me the opportunity to complete this research. reference alimin, r., & fajri, r. (2020). pergeseran dan pemertahanan bahasa pakpak dialek boang di kecamatan rundeng kota subulussalam. journal of education science, 8(1), 429–441. http://www.jurnal.unsyiah.ac.id/mb/article /view/22155 ardi, y., andreswari, d., & setiawan, y. (2017). rancang bangun aplikasi kamus istilah kedokteran dengan menggunakan algoritma boyer-moore berbasis android. jurnal rekursif, 5(3), 346–359. argakusumah, k. w., & hansun, s. (2014). implementasi algoritma boyer-moore pada aplikasi kamus kedokteran berbasis android. ultimatics (jurnal teknik informatika), 6(2), 70–78. https://doi.org/10.31937/ti.v6i2.340 basaria, i. (2014). pentopikalan dalam bahasa pakpak-dairi. litera, 13(1), 140–154. https://journal.uny.ac.id/index.php/litera/ar ticle/view/1909/1564 darmawan, r. i., setianingrum, a. h., & arini, a. (2018). implementasi algoritma boyer moore pada aplikasi kamus istilah kebidanan berbasis web. query: jurnal sistem informasi, 2(1), 53–62. http://jurnal.uinsu.ac.id/index.php/query/a rticle/view/1574 hendra, a., & destari, r. a. (2015). sistem pakar pengidentifikasi kerusakan water heater ariston dengan menggunakan metode backward chaining berbasis web. csrid (computer science research and its development journal), 5(1), 11–30. http://piwik.potensi 125 utama.ac.id/index.php/csrid/article/view/ 33 lengkong, h. n., sinsuw, a. a. e., & lumenta, a. s. . (2015). perancangan penunjuk rute pada kendaraan pribadi menggunakan aplikasi mobile gis berbasis android yang terintegrasi pada google maps. e-journal teknik elektro dan komputer, 2015(2015), 18–25. munandar, a., rosnelly, r., & sianturi, c. j. m. (2020). rancang bangun aplikasi keamanan data teks menggunakan algoritma stream cipher. jurnal mahasiswa fakultas teknik dan ilmu komputer, 1(1), 407–416. http://ejournal.potensiutama.ac.id/ojs/index.php/ftik/article/vie w/876 nikmatuzaroh, r. e. (2018). evaluasi tingkat kepuasan pasien terhadap pelayanan kefarmasian di apotek wilayah kota yogyakarta provinsi daerah istimewa yogyakarta. in fkik umy. universitas muhammadiyah yogyakarta. priyanto, a., & ulinnuha, f. (2017). perancangan aplikasi penerjemah bahasa indonesia ke bahasa jawa untuk media bantu belajar siswa smk salafiyah berbasis android. ijns.org indonesian journal on networking and security, 6(4), 2302–5700. puspita, & wayahdi, m. r. (2015). analisis kombinasi metode caesar cipher , vernam cipher , dan hill cipher dalam proses kriptografi. seminar nasional teknologi informasi dan multimedia 2015, februari, 43– 48. https://www.academia.edu/download/3658 3960/analisis_kombinasi_metode_caesar_ci pher__vernam_cipher__dan_hill_cipher_dala m_proses_kriptografi.pdf ramadhansyah. (2013). perancangan aplikasi kamus bahasa gayo dengan menggunakan metode boyer-moore. teknik informatika, stmik budidarma medan, iv(12110817), 118–122. sukirman, s. (2021). karya sastra media pendidikan karakter bagi peserta didik | jurnal konsepsi. jurnal konsepsi, 10(1), 17– 27. https://p3i.my.id/index.php/konsepsi/articl e/view/4 tondo, f. h. (2009). kepunahan bahasa-bahasa daerah: faktor penyebab dan implikasi etnolinguistis. jurnal masyarakat & budaya, 11(2), 277–296. widianto, e. (2018). pemertahanan bahasa daerah melalui pembelajaran dan kegiatan di sekolah. jurnal kredo, 1(2), 1–13. http://jurnal.umk.ac.id/index.php/kredo/art icle/view/2096 zulham, m., kurniawan, h., & rahmad, i. f. (2014). perancangan aplikasi keamanan data email menggunakan algoritma enkripsi rc6 berbasis android. seminar nasional informatika, 1(1), 96–101. http://ejournal.potensiutama.ac.id/ojs/index.php/snif/article/view /221 zuska, f. (2013). politik etnisitas dalam pemekaran daerah. antropologi indonesia, 33(3). https://doi.org/10.7454/ai.v33i3.2464 126 277 predicting the bitcoin price using linear regression optimized with exponential smoothing indah suryani 1*), hani harafani 2 informatika universitas nusa mandiri www.nusamandiri.ac.id indah.ihy@nusamandiri.ac.id 1*), hani.hhf@nusamandiri.ac.id 2 (*) corresponding author abstrak bitcoin merupakan salah satu mata uang kripto yang paling popular saat ini. di dalam kondisi pandemic yang melanda dunia saat ini akibat covid-19, maka bitcoin diharapkan dapat dijadikan sebagai sebuah investasi ketika tingkat ketidakpastian ekonomi sedang tinggi. pada penelitian ini, data yang digunakan adalah data harga bitcoin yang termasuk ke dalam data deret waktu. salah satu metode yang umum digunakan untuk prediksi dalam deret waktu adalah metode regresi linear. untuk dapat mengembangkan hasil prediksi tersebut, digunakan teknik transformasi data menggunakan metode yang popular yaitu exponential smoothing. pada metode exponential smoothing, dilakukan optimasi parameter alpha untuk dapat mendongkrak hasil prediksi dari regresi linear. dan dari hasil ekperimen yang dilakukan, terbukti bahwa optimasi parameter alpha pada exponential smoothing mampu meningkatkan performa prediksi regresi linear dengan hasil perbandingan rmse dengan uji t telah menghasilkan hasil perbedaan yang signifikan. kata kunci: bitcoin; linear regresi; exponential smoothing abstract bitcoin is one of the most popular cryptocurrencies today. in the current pandemic conditions that hit the world due to covid-19, bitcoin is expected to be used as an investment when the level of economic uncertainty is high. in this study, the data used is bitcoin price data which is included in time series data. one of the commonly used methods for prediction in time series is the linear regression method. to be able to develop the prediction results, a data transformation technique is used using the popular method, namely exponential smoothing. in the exponential smoothing method, optimization of the alpha parameter is carried out to be able to boost the prediction results from linear regression. and from the experimental results, it is evident that the optimization of the alpha parameter in exponential smoothing can improve the prediction performance of linear regression with the results of the comparison of rmse with the t-test which has resulted in significant differences. keywords: bitcoin; linear regression; exponential smoothing introduction bitcoin having received increased levels of attention from the media and investors alike in recent years (kalyvas et al., 2020). so making bitcoin one of the most popular among all cryptocurrencies. in line with (jareño et al., 2020), they stated that in recent years, cryptocurrency markets have become much more popular, so cryptocurrencies may have moved to the category of investment assets. much research on bitcoin has focused on the price discovery process and market efficiency in the bitcoin market (tsang & yang, 2020). there are several bitcoin exchanges and the price difference between them is large and changes over time (tsang & yang, 2020). the global covid-19 pandemic has disrupted normal business and affected sustainable economic development in many countries. however, it seems that the economic uncertainty following the covid-19 containment measures is supporting the cryptocurrency market signal (sarkodie et al., 2021). in line with (kalyvas et al., 2020), their findings indicate that bitcoin may possess hedging http://creativecommons.org/licenses/by-nc/4.0/ 278 properties against economic uncertainty; therefore, it may be beneficial for investors to consider this cryptocurrency as an investment when economic uncertainty is high. the linear regression model is representative of the most well-known family of regression models, this model consists of a linear function that underlies the class of hypotheses (vercellis, 2009). linear regression is a statistical technique that describes a linear relationship between two variables, namely the dependent variable and the independent variable (aslanyan, 2021; mondal & rehena, 2020). linear regression (lr) can be useful not only for discovering patterns in experimental data but also as a baseline for benchmarking and validating new analysis techniques (zakeri et al., 2020), especially novel or unfamiliar ones. linear regression is also one of the prediction methods in machine learning that is quite popular for researchers to develop, as done by (huang & hsieh, 2020), (matiz & barner, 2020), and (patel & kiran, 2019). a relevant problem that often faced by practitioners regarding the dynamic nature of time series is the selection of a particular exponential smoothing model. for example, the choice between adopting a local linear trend and simple exponential smoothing is usually driven by the detection (or absence) of a trend in the data (sbrana & silvestrini, 2014). however, during the course of a business cycle, the trend dynamics of a series are sometimes not constant over time and may vary (sbrana & silvestrini, 2013). data transformation can be in the form of smoothing, aggregation, generalization, normalization, and attribute construction or feature construction. one of the functions of the smoothing technique is to remove noise from the data. and exponential smoothing is one of those smoothing techniques (han & kamber, 2006). another advantage of exponential smoothing is that it can consider trends and seasonal effects of the data so that it can produce estimates with simple formulas (tratar, 2015). in addition, exponential smoothing also can beat many other advanced methods (beaumont, 2014). therefore, exponential smoothing is also widely used to develop time series prediction models, as was done by previous research in (yager, 2013),(koehler et al., 2012), and (suryani, 2015). based on the literature, it is interesting in this study to be able to predict the price of bitcoin by developing a linear regression method which developed by transforming the data using exponential smoothing. which in previous studies, efforts to improve performance with exponential smoothing used for the gold price dataset and were directly carried out on the neural network method without first comparing with other machine learning methods. while in this study, optimization with exponential smoothing carried out after comparing the rmse values between the three machine learning methods and used to predict bitcoin prices. research methods types of research this type of research is currently being carried out in the form of quantitative research in the form of experimental research. time and place of research this research used secondary data from https://www.investing.com/crypto/bitcoin/histor ical-data. these data records collected from 01 march 2017 until 05 march 2021 procedure in this study, the dataset in the form of bitcoin closing prices was processed first with data pre-processing techniques such as set roles, normalize and windowing. the role set is used to define labels and id. normalize is used to normalize the data and windowing is used to break the closing price attribute into 5 parts, namely 5 input data and 1 output data. modeling in this research is the optimization of the alpha parameter in exponential smoothing to improve performance on prediction results using linear regression as shown in figure 1. the first thing to do is to process a dataset in the form of bitcoin closing prices with pre-processing techniques such as set roles, normalize and windowing. the role set is used to define labels and id. normalize is used to normalize data using binary sigmoid activation function and windowing is used to break the closing price attribute into 5 parts, namely 5 input data and 1 output data. furthermore, exponential smoothing will used to optimize the performance of linear regression by optimizing its alpha parameter. after that, the new data will be produced and then processed by linear regression method using 4 future selection options in the form of t-test, m5prime, greedy, and iterative-test. the processing is carried out using the 10 fold cross-validation technique, namely by dividing the training and testing data. then the rmse value will obtained from each experiment carried out and then a comparison is made. http://creativecommons.org/licenses/by-nc/4.0/ 279 figure 1. proposed method data, instruments, and data collection techniques the data collected is in the form of historical data on bitcoin prices which includes the attributes of date, opening price, highest price, low price, closing price, volume_btc, volume_currency, and weighted prices. the attributes used to be processed are only the attributes of the date and closing price. which is contains 1.170 records. data analysis technique the data used in this research is time-series data in the form of historical data from bitcoin prices. wherefrom the bitcoin price data, only one price data attribute is used in the form of the closing price data only. as shown in table 1. below. table 1. samples of bitcoin prices data date closing price 05/03/2021 56.826 05/02/2021 57.016 05/01/2021 57.700 4/30/2021 56.803 4/29/2021 53.006 4/28/2021 54.456 4/27/2021 55.067 4/26/2021 53.297 4/25/2021 48.075 4/24/2021 50.955 based on this data, there are two attributes, namely the date and closing price. then made arrangements to determine the id and label attributes. we specify the date attribute as the id attribute and the closing price attribute as the label. furthermore, the data normalization was carried out using the activation function of the binary sigmoid. then the windowing technique is carried out because the data used is in the form of univariate data. after that, the data is ready to be processed using machine learning. from the experiments conducted, the performance of several methods in machine learning was tested, namely using k-nearest neighbor, neural network, and linear regression. based on the rmse results generated from the three methods, the method that produces the highest average rmse is chosen and then optimized with exponential smoothing. results and discussion evaluation the data that is ready to use after preprocessing is then predicted by experimenting with three methods. then an evaluation will be made of the average rmse value generated from each of these methods. first, the experiment was carried out using the knn method. in this experiment, the k parameter optimization was carried out on the knn with 4 experimental samples. the results can be seen in table 2 below. the average rmse value generated from the knn method is 0.608. table 2. experiments result using knn no. k rmse 1 0.7 0.5 2 0.5 0.48 3 0.3 0.478 4 0.1 0.974 average 0.608 the next experiment is to use the neural network method. in this experiment, optimization was carried out on the learning rate and momentum parameters with 4 experiments. the result obtained is to get an average rmse value of 0.497 as shown in table 3 below. table 3. experiments result using neural network no. lr mom rmse 1 0.01 0.9 0.507 2 0.001 0.9 0.435 3 0.01 0.5 0.454 4 0.001 0.5 0.59 http://creativecommons.org/licenses/by-nc/4.0/ 280 average 0.497 the third method that was tested is linear regression. this experiment was carried out with 4 different feature selections as listed in table 4. the resulting average rmse value was 0.451. and it turns out that this method produces the lowest rmse value, which means that this method produces better predictive results. table 4. experiments result using linear regression no. feature selection rmse 1 t-test 0.451 2 m5prime 0.452 3 greedy 0.449 4 iterative-t test 0451 average 0.451 from the experiments that produced the best average rmse value, then it was made to improve performance by using the exponential smoothing method. then an experiment was carried out by optimizing the results of linear regression with exponential smoothing. the experiment was carried out by optimizing the alpha value in exponential smoothing with 4 feature selections in linear regression. and the results of these experiments can be seen in table 4 below. table 5. experiments result using linear regression + exponential smoothing no. alpha feature selection rmse 1 0.5 t-test 0.229 2 0.3 t-test 0.157 3 0.1 t-test 0.175 4 0.5 m5prime 0.229 5 0.3 m5prime 0.157 6 0.1 m5prime 0.178 7 0.5 greedy 0.229 8 0.3 greedy 0.157 9 0.1 greedy 0.178 10 0.5 iterative-t test 0.229 11 0.3 iterative-t test 0.157 12 0.1 iterative-t test 0.178 average 0.188 by performing optimization using exponential smoothing in the linear regression method, it turns out that it can produce a lower rmse value with an average rmse value of 0.188. this value is generated over 12 experiments. and it can be seen that the choice of features does not affect increasing the rmse value, while the optimization of the alpha value on exponential smoothing has a sufficiently good impact on the increase in the rmse value. validation to prove whether there is a difference, and how significant the difference is between the usual linear regression method and the proposed method, in the form of optimizing linear regression using exponential smoothing, so it validates with a t-test. table 6. rmse comparison between lr and lr+es using t-test variable 1 variable 2 mean 0.45075 0.18475 variance 1.58333e-06 0.0009562 5 observations 4 4 pearson correlation 0.070674182 hypothesized mean difference 0 df 3 t stat 17.14049415 p(t<=t) one-tail 0.000216309 t critical one-tail 2.353363435 p(t<=t) two-tail 0.000432618 t critical two-tail 3.182446305 from the results of the t-test in table 6, it produces a t-table value of 17.14049415, and tcount value of 3.182446305, then the t-table value is greater than the t-count value. this means that there is a difference in alias h1 is accepted and h0 is rejected. this difference also shows a significant value. this can be seen at the p-value which is less than 0.05 yaitu semester 0.000432618. conclusions and suggestions conclusion based on the experiments conducted, this study uses three machine learning methods, namely k-nearest neighbor, neural network and linear regression. from the three methods, it is known that the linear regression method shows the highest average rmse value of 0.451. after that, efforts were made to improve linear regression performance with exponential smoothing. it is known that the optimization of the alpha parameter in exponential smoothing can provide an average rmse value of 0.188 and can provide a significant difference in the classical linear regression method. where in previous studies, efforts to increase performance with exponential smoothing were directly carried out on the neural network method without first comparing what machine learning method has a better rmse. that study also used another dataset, which was the gold price dataset. meanwhile, in this study, optimization with exponential smoothing was carried out after http://creativecommons.org/licenses/by-nc/4.0/ 281 knowing the method that produced the most superior rmse for predict the bitcoin prices. and it can be concluded that exponential smoothing can improve the performance of linear regression to be able to predict bitcoin prices. suggestion from the results of the research conducted, it turns out that exponential smoothing can provide increased performance in predictions using the linear regression method. so in future research, it is hoped that the use of exponential smoothing will be developed as a method in pre-processing data to improve the performance of other machine learning methods. other experiments are also expected to be carried out with different datasets. references aslanyan, t. k. (2021). fundamentals of statistics for data scientists and analysts. towards data science. https://towardsdatascience.com/fundament als-of-statistics-for-data-scientists-and-dataanalysts-69d93a05aae7 beaumont, a. n. (2014). data transforms with exponential smoothing methods of forecasting. international journal of forecasting, 30(4), 918–927. https://doi.org/10.1016/j.ijforecast.2014.03. 013 han, j., & kamber, m. (2006). mining stream, timeseries and sequence data. in data mining: concepts and techniques (vol. 54, pp. 468– 473). huang, c. h., & hsieh, s. h. (2020). predicting bim labor cost with random forest and simple linear regression. automation in construction, 118(may), 103280. https://doi.org/10.1016/j.autcon.2020.1032 80 jareño, f., gonzález, m. de la o., tolentino, m., & sierra, k. (2020). bitcoin and gold price returns: a quantile regression and nardl analysis. resources policy, 67(february). https://doi.org/10.1016/j.resourpol.2020.10 1666 kalyvas, a., papakyriakou, p., sakkas, a., & urquhart, a. (2020). what drives bitcoin’s price crash risk? economics letters, 191(september 2011), 1–5. https://doi.org/10.1016/j.econlet.2019.1087 77 koehler, a. b., snyder, r. d., ord, j. k., & beaumont, a. (2012). a study of outliers in the exponential smoothing approach to forecasting. international journal of forecasting, 28(2), 477–484. https://doi.org/10.1016/j.ijforecast.2011.05. 001 matiz, s., & barner, k. e. (2020). conformal prediction based active learning by linear regression optimization. neurocomputing, 388, 157–169. https://doi.org/10.1016/j.neucom.2020.01.0 18 mondal, m. a., & rehena, z. (2020). road traffic outlier detection technique based on linear regression. procedia computer science, 171(2019), 2547–2555. https://doi.org/10.1016/j.procs.2020.04.276 patel, d. r., & kiran, m. b. (2019). a non-contact approach for surface roughness prediction in cnc turning using a linear regression model. materials today: proceedings, 26(xxxx), 350– 355. https://doi.org/10.1016/j.matpr.2019.12.02 9 sarkodie, s. a., ahmed, m. y., & owusu, p. a. (2021). covid-19 pandemic improves market signals of cryptocurrencies–evidence from bitcoin, bitcoin cash, ethereum, and litecoin. finance research letters, january, 102049. https://doi.org/10.1016/j.frl.2021.102049 sbrana, g., & silvestrini, a. (2013). forecasting aggregate demand: analytical comparison of top-down and bottom-up approaches in a multivariate exponential smoothing framework. international journal of production economics, 146(1), 185–198. https://doi.org/10.1016/j.ijpe.2013.06.022 sbrana, g., & silvestrini, a. (2014). random switching exponential smoothing and inventory forecasting. https://www.bancaditalia.it/pubblicazioni/t emi-discussione/2014/20140971/en_tema_971.pdf suryani, i. (2015). penerapan exponential smoothing untuk transformasi data dalam meningkatkan akurasi neural network pada prediksi harga emas. journal of intelligent systems, 1(2), 67–75. tratar, l. f. (2015). int . j . production economics. intern. journal of production economics, 161, 64–73. https://doi.org/10.1016/j.ijpe.2014.11.019 tsang, k. p., & yang, z. (2020). price dispersion in bitcoin exchanges. economics letters, 194, 109379. https://doi.org/10.1016/j.econlet.2020.1093 79 http://creativecommons.org/licenses/by-nc/4.0/ 282 vercellis, c. (2009). business intelligence: data mining and optimization for decision making. in business intelligence: data mining and optimization for decision making. https://doi.org/10.1002/9780470753866 yager, r. r. (2013). exponential smoothing with credibility weighted observations. information sciences, 252, 96–105. https://doi.org/10.1016/j.ins.2013.07.008 zakeri, z., mansfield, n., sunderland, c., & omurtag, a. (2020). cross-validating models of continuous data from simulation and experiment by using linear regression and artificial neural networks. informatics in medicine unlocked, 21(july), 1–6. https://doi.org/10.1016/j.imu.2020.100457 http://creativecommons.org/licenses/by-nc/4.0/ microsoft word 14_236-jri-32-187-194_tyas 187 implementation of inventory information system design using economic order quantity method frieyadie1,*, tyas setiyorini 2 1 sistem informasi, teknik informatika universitas nusa mandiri, jakarta, indonesia www.nusamandiri.ac.id 1*) frieyadie@nusamandiri.ac.id, 2 tyas.setiyorini@gmail.com *) corresponding author abstrak permasalahan penelitian yang dihadapi adalah diantaranya biaya pemesanan barang yang selalu berubah-ubah setiap ada pemesanan. pendataan order produk yang kurang baik dan kurang optimalnya penanganan order produk hal ini dapet merugikan perusahaan. untuk memecahkan ketidak baikan pengangan manajemen inventory ini, maka menggunakan metode economic order quantity (eoq) dimana terbukti efektif dalam mengatasi permasalahan tersebut. kontribusi yang dihasilkan dengan membangun sistem informasi manajemen inventory, supaya permasalahan yang dihadapi tidak terulang lagi. tujuan dari penelitian ini supaya biaya pemesanan barang menjadi lebih stabil dan menajad lebih optimal dalam penanganan order produk. kata kunci: sistem informasi; economic order quantity (eoq) model waterfall; persediaan barang abstract the research problems faced are among others the cost of ordering goods which always changes every time there is an order. poor product order data collection and less than optimal handling of product orders can harm the company. to solve the problem of controlling inventory management, the economic order quantity (eoq) method is used, which is proven to be effective in overcoming these problems. contribution is generated by building an inventory management information system so that the problems faced are not repeated. the purpose of this study is to make the cost of ordering goods more stable and more optimal in handling product orders. keywords: information systems; economic order quantity (eoq) waterfall model; inventory introduction pt. msj is a company engaged in manufacturing. where in the process of ordering raw materials, incoming or outgoing goods still use a manual process, namely by using paper to record them. likewise with the stock items still using paper. of course, this can create big risks that will occur. based on observations at pt. msj has several obstacles, namely difficulties in finding data on a raw material stock (ramdhany & fitriasih, 2019) (humaeni, muanas, & sudradjat, 2019), data processing goods, supplier data, and raw material purchase data. in the process of making reports, the company still takes a long time to prepare reports on raw material stock, incoming goods, and outgoing goods that still use paper records which at any time can be lost and damaged by rain and dirty in uncertain conditions. the current purchasing and inventory processes are deemed not going well and efficiently, where all processes are still running manually (cahyana, yuwono, & asmoro, 2012)(pudjiarti, puspitasari, & septyawati, 2019)(atikah, 2017), do not have good control, and do not have good data collection (apriani, aisyah, & anggraini, 2019). as for some of the problems faced, including the cost of ordering goods which always changes every time there is an order (tarsono & khotimah, 2018). this ordering cost is also influenced by the type of goods, the origin of the purchase of the goods, the amount of stock. the process of making documents that still use paper documents. frequent document loss (fatmawati & munajat, 2018)(sidik, waluyo, & susilawati, 2018), damage to documents, and the creation of double documents. difficulty in searching for historical data, and difficulty in making inventory reports (setiyanto, nurmaesah, & rahayu, 2019). the existing system has not been able to provide accurate stock information. based on previous research using the eoq method to reduce errors in data collection of ordered products (mujiastuti, meilina, & rully, 2018), so that the optimal ordering frequency can be found (anwar, mikhratunnisa, & cahyono, 2019). the method proposed in this study is the economic jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.174 188 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional order quantity (eoq) method. this method can answer the problems faced by pt. msj, which can calculate the exact reorder point (nasution & indriya, 2020). optimally, it can calculate the reorder quantity. based on the trend of using the eoq method (figure 1) in 1 (one) year in 2020. the eoq method still ranks as a widely used method for solving inventory management problems. figure 1. trends in the use of the eoq method in 2020. this inventory information system development model adopts the waterfall model, where the flow of system development is clearer based on the phases in the waterfall model. the current research contribution refers to the application system designed and implemented at pt. msj. the purpose of this research is to avoid document loss, make it easier to produce inventory reports, and be able to see accurate and correct stocks. given the breadth of the root of the raw material inventory information system, the boundaries or coverage will be made to be analyzed. the system discussed starts from the ordering process to suppliers, warehouse stock, product categories, goods data, and releasing goods. in the process of inputting incoming goods acceptance transactions, goods releasing transactions, and printing of goods stock data reports. research methods data collection technique in collecting data and information, the author researches to obtain the necessary data, by methods, including: a. observation the observation process was carried out by observing directly at pt. msj is a system process that runs, both from the initial purchase submission until the goods being ordered are received by the warehouse so that the research process can run well and find out the needs and shortcomings. b. interview the interview method is a direct question and answer process to the executive, general administration, and logistics administration to find out problems that exist in the raw material supply process. c. literature review the literature study process carried out and various reference sources both internal media, journal articles related to purchasing and inventory systems. economic order quantity (eoq) one of the methods used to control goods in a company (zahirah & arista, 2019). the existence of this eoq method makes inventory planning better. some things that need to be considered in the procurement of goods, namely ordering costs and storage costs. this ordering cost will continue to increase because usually, the ordering costs will continue to change, along with the number of orders for goods from suppliers. storage costs are also a burden on the company because storage costs are also constantly changing based on the number of items stored. eoq has a calculation using a formula like the following: 189 ��� � ��� � � .................................................................... (1) from equation 1, calculating the economic order quantity, where: r: ordering fee (order preparation and machine storage) per order s: estimated use or demand per period p: storage cost per unit per year eoq method can be implemented several questions can be done in the following conditions. a. the demand for a product is constant, uniform, and known (deterministic). b. the price per unit of product is constant. c. storage cost per unit per year (p) is constant. d. order cost per order (r) is constant. e. the time between order placed and goods received (lead time, l) is constant. f. there is no shortage of goods or "back orders". system development model the waterfall model is sometimes called the classic life cycle (pressman & maxim, 2015), suggests a systematic and sequential approach to software development starting with the specification of customer requirements and progressing through planning, modeling, construction, and deployment, culminating in the ongoing support of completed software. figure 2. waterfall model the following is an explanation of the waterfall model which is in. a. communication (project initiation & requirements gathering) time to start technical work, the developer must meet with customers to establish communication, to understand and achieve the goals of the system to be achieved. the result of this communication is the initialization of the project, such as the need for functional characteristics of each user in the system, analyzing the problems faced, and collecting the necessary data. b. planning (estimating, scheduling, tracking) the 2nd (two) next step is the planning stage which describes the estimation of the technical tasks to be carried out, the risks that may occur, the resources needed to create the system, the work products to be produced, the work plans that will be carried out, and the tracing of the system work processes. c. modeling (analysis & design) step 3 (three) is the stage of designing and modeling system architecture, with a focus on designing data structures, software architecture, interface displays, and program algorithms. the goal is to better understand the overall picture of what will be done. d. construction (code & test) stage 4 (four) of the process of translating the design form into program code or changing the result of the design to a machine-readable language. after the coding is complete, testing is carried out on the system and also the code that has been created. the goal is to find errors that might be corrected later. e. deployment (delivery, support, feedback) the fifth stage (five) stages of software implementation to customers, software repair, software evaluation, and software development are based on the feedback given so that the system can continue to run and develop according to its function. results and discussion the following is a discussion of system development using the waterfall model. each stage of the discussion will follow the flow of the waterfall model stage. communication (project initiation & requirements gathering) the following is a specification of the needs of each user of the raw material inventory information system. 1. purchasing section a. can log into the system b. can manage product data b. can manage supplier data c. can manage purchase order data 2. warehouse section a. can log into the system b. can manage incoming items b. can manage outgoing goods planning (estimating, scheduling, tracking) 1. estimating implementation of estimates in planning the technical tasks to be carried out, the risks that may jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.174 190 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional occur, the resources needed to create the system, the work products to be produced analyst system. in charge of carrying out system analysis to be built programmer. in charge of translating the results of analysis and design that have been made in code with a programming language that suits the needs and objectives to be made tester system. in charge of testing the application that is built whether it runs by the planned functional needs 2. scheduling dan tracking figure 3 is the implementation of work plans that will be carried out in the construction of an inventory information system and also tracking work. implementation for 16 (sixteen weeks). figure 3. inventory information system design modeling (analysis & design) some modeling for information systems analysis using uml will be discussed by describing use case diagram modeling. a. use case diagram inventory information system figure 4. use case diagram inventory information system table 1 explains, one of the use case manage eoq data in figure 4. table 1. use case manage eoq data scenarios use case name : manage eoq data use case description : purchasing dept. manage eoq data, by adding, update, deleting, and printing data. actors : purchasing dept. pre-condition : the system must be connected to an intranet network. purchasing dept. must be logged in post condition : after successful login, a successful message is displayed for eoq data main scenarios serial no. step purchasing dept 1 click add to input eoq data 2 click view data to display material data 3 click edit data to change material data 4 click clear data to change material data 5 permit accessing system by access rights extensions 1a the added eoq data form appears 2a the eoq data view form appears 3a the eoq data edit form appears 4a clear eoq data message appears 5a print eoq data will appear uc use case inv entory information system inventory information system purchasing dept. login manage material data manage supplier data manage eoq data manage purchasing order manage incoming material warehouse manage outgoing material create a material requirements letter 191 b. eoq data browse design figure 5 is an eoq data browse plan, which displays the overall eoq data. purchasing dept. can manage eoq data, such as: add, view, edit, delete and print data. figure 5. eoq data browse design c. eoq data input design figure 6 is the form used to add eoq data, some field items that must be inputted by the purchasing dept. figure 5. eoq data browse design construction (code & test) a. economic order quantity algorithm design the following algorithm is written for an inventory information system application. begin number r, s, p, l input r input s input p input l input hpt (2*r*s)/p eoq (p*eoq/2)+(r*s*eoq) tc s/eoq frq hpt/frq dh_eoq l*d/hpt rop output eoq output tc output frq output dh_eoq output rop end b. economic order quantity function the following functions will be used in the inventory information system. jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.174 192 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional public function eoq($r,$s,$p){ $eoq=round(sqrt((2*$r*$s)/$p)); return $eoq; } public function tc($r,$s,$p,$eoq){ $tc = round(($p*$eoq/2)+($s*$r/$eoq)); return $tc; } public function frq($r,$eoq){ $frq = round($r/$eoq); return $frq; } public function durasi($jhk,$frq){ $durasi = round(($jhk/$frq)); return $durasi; } public function rop($l,$r,$jhk){ $rop = round(($l*$r)/$jhk); return $rop; } c. system performance testing figure 6. system performance testing testing system performance in figure 6, users involved as many as 8 users. the response time from the initial minute to the last minute of testing was set for 10 minutes of listening testing, averaging 0.92 seconds, reading pdf data files an average of 1.03 seconds. average response time with page reading of 0.92 seconds. deployment (delivery, support, feedback) the main purpose of this stage is to explain how software is implemented into hardware, also to visualize how software interacts with hardware to carry out its functionality.. a. delivery after completing the development of the inventory information system, the developer then submits it to the end user to be installed on the company's server. figure 7. system performance testing in figure 7, it can be concluded that the minimum specification for running an inventory information system application is that on the server side it requires a webserver, namely apache web server, with the application installed on the webserver by accessing index.php. the database management system used by mysql database. on the client-side, deployment deployment diagram inv entory information system «devi ce» webserv er index.php «device» web serv er mysql database «device» user dev ice «appl ication» web brow ser port 80 193 using devices that are not limited to pcs, can also be tablets, smartphones, laptops. when accessing it with a web browser. b. feedback feedback in table 2, in the form of a user acceptance test, is information on the results of the end user's reaction to the inventory application, someone's performance on an assignment, etc. which is used as a basis for improvement. tabel 2. user acceptance test no a list of questions percentage 1 is the eoq data management dashboard easy to operate 91% 2 is eoq data input understandable and easy to use? 93% 3 is change eoq data understandable and easy to use 93% 4 does appear data eoq understands and is easy to use 95% 5 is the calculation process as expected? 93% 6 is the process of accessing this inventory application fast? 92% 7 is the data access process in this inventory application fast? 92% 8 is this inventory application sufficient? 96% table 2, is the stage for testing user acceptance of, in general, users who test the inventory information system accept this application. conclusion in general, this inventory information system can help users implement the company's existing inventory of incoming and outgoing goods. the application of the eoq method can determine the volume and frequency of material orders needed to meet production needs and reduce the cost of each order. references anwar, r. s., mikhratunnisa, & cahyono, t. d. (2019). perancangan aplikasi berbasis android dengan metode economic order quantity di pt. samawa tirta alam sumbawa. jurnal tambora, 3(2), 49–59. retrieved from http://www.jurnal.uts.ac.id/index.php/tamb ora/article/view/289 apriani, d., aisyah, e. s., & anggraini, l. (2019). rancang bangun sistem informasi inventory peralatan komputer berbasis website pada pt indonesia toray synthetics. technomedia journal, 4(1), 15–29. https://doi.org/10.33050/tmj.v4i1.997 atikah, a. (2017). analisa dan perancangan sistem informasi pengadaan bahan baku pada pt.xyz. string (satuan tulisan riset dan inovasi teknologi), 1(2), 109. https://doi.org/10.30998/string.v1i2.1030 cahyana, n. h., yuwono, b., & asmoro, a. y. (2012). pengembangan sistem informasi persediaan barang berbasis web di pt . putera agung setia. pengembangan sistem informasi persediaan barang berbasis web di pt . putera agung setia, 9(semnasif), 252–258. yogjakarta: upn ”veteran” yogyakarta. retrieved from http://103-23-20161.isi.cloud.id/index.php/semnasif/article/ view/1106 fatmawati, f., & munajat, j. (2018). implementasi model waterfall pada sistem informasi persediaan barang berbasis web (studi kasus: pt.pamindo tiga t). jurnal media informatika budidarma, 2(2), 1–9. https://doi.org/10.30865/mib.v2i2.559 humaeni, a., muanas, m., & sudradjat, s. (2019). peranan program yongjin erp sebagai sistem informasi akuntansi pengendalian persediaan bahan baku. jurnal ilmiah akuntansi kesatuan, 7(1`), 213–218. https://doi.org/10.37641/jiakes.v7i1`.201 mujiastuti, r., meilina, p., & rully, m. a. (2018). implementasi metode economic order quantity (eoq) pada sistem informasi produksi kopi. jurnal sistem informasi, teknologi informatika dan komputer, 8(2), 119–126. retrieved from https://jurnal.umj.ac.id/index.php/justit/article/download/.../2376 nasution, a., & indriya, c. (2020). pembelian bahan baku optimal ready mix concrete dengan metode economic order quantity. jurnal sistem teknik industri, 22(2), 25–32. https://doi.org/10.32734/jsti.v22i2.3827 pressman, r. s., & maxim, b. r. (2015). software engineering: a practitioner’s approach. in mcgraw-hill education (eighth, vol. 8). new york city: mcgraw-hill education. pudjiarti, e., puspitasari, e., & septyawati, a. a. (2019). sistem informasi persediaan barang berbasis dekstop pada pt. ultra sakti. jusikom : jurnal sistem komputer musirawas, 4(02), 111–119. https://doi.org/10.32767/jusikom.v4i2.584 ramdhany, t., & fitriasih, n. (2019). aplikasi persediaan barang jadi pada pt refika jurnal riset informatika vol. 3, no. 1 december 2020 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i1.174 194 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional aditama bandung. in jurnal lpkia (vol. 12). retrieved from http://jurnal.lpkia.ac.id/index.php/jkb/articl e/view/230 setiyanto, r., nurmaesah, n., & rahayu, n. s. a. (2019). perancangan sistem informasi persediaan barang studi kasus di vahncollections. jurnal sisfotek global, 9(1), 137–142. https://doi.org/10.38101/sisfotek.v9i1.26 7 sidik, a., waluyo, e. t. b., & susilawati, s. (2018). perancangan sistem informasi laporan persediaan barang jadi pt duta prima plasindo. jurnal sisfotek global, 8(1), 7–12. retrieved from https://journal.stmikglobal.ac.id/index.php/s isfotek/article/view/161 tarsono, o., & khotimah, s. (2018). peranan economic order quantity dalam peningkatan efisiensi pengelolaan persediaan pada pt. martina berto tbk. jurnal stei ekonomi, 26(2), 217–229. https://doi.org/10.36406/jemi.v26i2.225 zahirah, s. h., & arista, a. (2019). pengendalian persediaan dengan menggunakan metode economy order quantity pada distributor makanan. computer and science industrial engineering (comasie), 11(01), 32–41. retrieved from https://ejournal.itn.ac.id/index.php/valtech/ article/view/209 371 developing blended learning application utilizing articulate story line 3.0 intregrated with android based system efrizal siregar, nurianti sitorus, juwariah teknik grafika politeknik negeri media kreatif https://polimedia.ac.id/ efrizal_siregar@polimedia.ac.id, nurianti_torus@polimedia.ac.id, juwariah@polimedia.ac.id (*) corresponding author abstrak perkerkembangan ilmu pengetahuan dan teknologi di era digital four point zero memiliki dampak yang besar bagi dunia pendidikan. salah satunya adalah dengan memanfaatkan aplikasi e-learning dalam proses pembelajaran. akan tetapi, teknologi yang digunakan dalam pembelajaran ini terlalu bergantung dengan jaringan internet. oleh karena itu penelitian bertujuan untuk mengembangkan sebuah media berupa aplikasi e-learning berbasis andorid yang dapat digunakan secara online dan offline. penelitian ini menggunakan rancangan penelitian dan pengembangan menggunakan model addie. untuk membuat dan menguji produk tersebut dalam hal ini aplikasi elearning berbsasis android. prosedur penelitian ini dilakukan melalui 6 tahapan yaitu analisis kebutuhan, tahap desaian aplikasi, pengembangan, analasisis data, evaluasi, dan pengembangan produk akhir yang siap untuk digunakan. dari hasil uji validasi materi dan kelayakan media aplikasi yang dikembangkan sangat layak untuk digunakan. kata kunci: aplikasi, blended e-learning, android, offline-online abstract the development of science and technology in the digital era of four point zero has a great impact on the world of education. one of them is by utilizing e-learning applications in the learning process. however, the technology used in this learning is too dependent on the internet network. therefore, the research aims to develop a media in the form of an android-based e-learning application that can be used online and offline. this study uses a research and development design using the addie model. to create and test these products, in this case an android-based e-learning application. procedure this research was carried out through 6 stages, namely needs analysis, application design stage, development, data analysis, evaluation, and development of a final product that is ready to be used. from the results of the material validation test and the feasibility of the developed application media, it is very feasible to use. keywords: aplication, blended e-learning, android, offline-online introduction we are currently entering the digital four point zero era where the use of technology has entered various aspects of life. almost every activity or activity or work has utilized digital technology in its implementation. digital technology in the form of the use of computing connected to the internet makes everything unlimited. many things can be controlled from a distance with digital technology. in addition, the impact of the covid-19 pandemic has also contributed to changes in the pattern of human life (ardhana januar mahardhani, 2020; pantan & benyamin, 2020) to find solutions from the implementation of social distancing by utilizing space on digital technology. this condition also has an impact on the use of information and communication technology which results in more and more new technologies appearing in various aspects of life. rachmad and fragastia mentions that the system used in android is linux, thus providing an open platform for anyone to create their own applications (rahmad & fragastia, 2017). in the world of education, one application that is widely developed on android is the elearning application. the e-learning application is an application used in teaching and learning activities that utilize digital technology in its implementation (harahap, 2015). students can access learning materials in the form of pictures, 372 learning videos, powerpoints, assignments that have been prepared in the e-learning. some of the popular e-learning used are edmodo (ekayati, 2018), moodle (polhun, kramarenko, maloivan, & tomilina, 2021), google classroom (murtikusuma et al., 2019), and quipper (el iq bali et al., 2021). however, the application can only be used if the android device is connected to the internet. if the internet connection is not connected then the application cannot be used. this is one of the obstacles to using e-learning applications. where the internet network has not reached all parts of indonesia and the price of internet quota is relatively expensive and the application used also consumes a lot of internet quota. siregar and manurung in 2020 stated that research shows that there are significant differences in the creativity of prospective teacher students who apply blended learning. thus, it can be said that blended learning has an effect on creativity (siregar & manurung, 2020). khoiroh in 2017 stated that student learning outcomes using the blended learning model were higher than student learning outcomes using the direct learning model. students' motivation in participating in learning using the blended learning learning model is higher than the direct learning learning model. there is an interaction between blended learning and learning motivation on student learning outcomes (khoiroh & anifah, 2017). the results of the research conducted by darmawan and nashoih, showed that the mobile learning media was declared valid and worthy of being used as a learning medium, based on the validation of media and material experts with an average score of 3.46, so it was declared feasible. while the results of the trial showed the effectiveness of the media through the pretest and posttest scores which increased by 26.71, with an average value of 52.39 for pretest and 79.10 for posttest. this figure shows that the application of mobile learning media is able to significantly improve student learning outcomes, as well as support the blended learning model (darmawan & nashoih, 2019). based on the background described above, the researcher wants to develop a blended elearning application, which means it can be used offline and online. online is used when students download the application on the play store available on the android system. while offline is used to access all the material in the application in the form of documents, power points, learning videos and others that are run without using the internet. research methods this research uses quantitative research, with the addie research model (arifin, septanto, & wignyowiyoto, 2018). this research model consists of 5 stages, namely analysis, planning, development, implementation, and evaluation. in this study, researchers only carried out stages 1 to stage 3. the analysis stage is a needs assessment process, identifying problems and conducting analysis using interview instruments to participants (15 people) graphic engineering students who use e-learning applications in the learning process. the design stage (blue print), namely the stage of developing an e-learning application that answers problems at the analysis stage to create an e-learning application that can be used online or offline so that when learning takes place it does not only depend on internet connections (quota). the development stage is the stage for compiling and engineering e-learning applications that have been designed so that android-based e-learning applications can be used, design research model can be seen in figure 1.. analysis design development data analysis data interpretation problem: an e-learning application solution determination of the e-learning data interpretation data analysis data analysis data analysis figure 1. research model types of research this research uses a quantitative approach . his research uses quantitative research, with the addie research model. this research model consists of 5 stages, namely analysis, planning, development, implementation, and evaluation. the development of learning media contains 3 main components, namely (hikmah, saridewi, & agung, 2017). 373 a. development style this is the basis for improving the product to be produced. model development model can be in the form of procedural models, conceptual models and theoretical models. b. development procedure the development procedure is different from the development model because the development procedure shows the properties of the components in each development session, explains analytically the use of components in each development session and explains the bonds between components in the system. c. product trial. the product trials tested were expert testing (expert validation), limited-scale trials and broadscale trials. time and place of research this research will be carried out at the state polytechnic of creative media psdku medan in the graphic engineering study program. held in may-november 2021. research target/subject the target of this research is a product in the form of artyculate story line 3.0-based learning media that can be used online and offline specifically in the graphic material knowledge course. the population of this study were graphic engineering students totaling 15 people. while the expert validators are graphic design lecturers and lecturers who teach graphic material knowledge courses. procedure the steps in designing articulate storybased learning media are as follows: the plan, in the process of making this media begins with the planning process. at this stage, first determine the purpose of the learning media created, namely learning media that can be used on-line and off-line. design, from the information and data collected at the planning stage, the next stage you design the front page display and the articulated media page starting from the log-in view. design is necessary to give the site beauty. this can be a combination of unique colors, layouts, fonts used to make the web attractive and not boring for users. figure 2 here's the media background design. figure 2. designing articulate story-based learning media data, instruments, and data collection techniques data collection techniques using primary data and secondary data (janah, sukarelawati, & agustini, 2019). primary data in the form of data on the feasibility assessment of android-based elearning application products by it experts and the substance of the material obtained by questionnaires in the form of an assessment of the resulting e-learning application and data on the responses of lecturers and students to the material contained in the android-based e-learning application. which is generated. data analysis technique primary data and secondary data were then analyzed. the data analysis used is quantitative and qualitative. qualitative data in the form of a questionnaire validation sheet from an expert validator containing assessments, responses, suggestions and input. the eligibility criteria for android-based e-learning applications are expressed in percentages calculated using the formula in equation 1. while quantitative data are obtained from student perceptions through questionnaires which are then analyzed. 𝑃𝑟𝑒𝑠𝑒𝑛𝑡𝑎𝑡𝑖𝑜𝑛 𝑜𝑓 𝑒𝑙𝑖𝑔𝑖𝑏𝑖𝑙𝑖𝑡𝑦 𝑣𝑎𝑙𝑢𝑒 = 𝑠𝑐𝑜𝑟𝑒 𝑜𝑏𝑡𝑎𝑖𝑛𝑒𝑑 𝑚𝑎𝑥𝑖𝑚𝑢𝑚 𝑠𝑐𝑜𝑟𝑒 × 100% .............. (1) table 1. eligibility of blended e-learning application products no presentage qualification 1 81-100 very supportive 2 61-80 supportive 3 41-60 enough supportive 4 21-40 less supportive 5 0-20 not supportive eligibility of blended e-learning application products. data obtained from expert validation of learning materials has weaknesses: the type of spiritual labor needed described and given examples; full working characteristics are 374 described again; there are no examples of the types of unemployment. less explanationcomplete; efforts to improve the quality of trained workersgrouped for clarity. the steps that recommended is to fix things that are not appropriate suggested material experts with additional comments is to add types of technological unemployment. the conclusion is the validation results are material declared eligible for field trials with revisions according to suggestions. description of expert validation of learning outcome test instrument materials results and discussion the design of learning media based on articulate story line 3.0 was validated by 3 experts from the design department and graphic department at the state polytechnic of creative media who acted as expert validators. the expert validators of this study are material validators and two lecturers as media validators. this validator assesses every component in the articulate story line 3.0-based learning media in accordance with the guidelines for assessing the feasibility of learning media from wahono (2006). the results of the media feasibility assessment by the validator can be observed in table 1. table 2. recapitulation of media feasibility assessment results material aspect no from matery score learning disain 1 clarity of learning objectives 4 2 relevance of learning objectives 4 3 the suitability of the material with the learning objectives 4 4 appropriate use of learning strategies 4 5 interaktive 3 6 motivation study 4 7 kontekstuality 4 8 materi dept 4 9 easy to understand 4 10 sistematic 4 11 clarity of descriptions, discussions, examples, simulations and exercises 4 12 evaluation 4 table 3. recapitulation of media feasibility assessment results media aspect no from media score soft ware aspek 1 effective and efficient in the development and use of learning media. 4 2 maintenace (can be maintained/managed easily). 3 3 usability (easy to use and simple to operate) with or without an internet connection. 4 4 compatibility (learning media can be installed/run on various existing hardware and software) 4 5 reusable (part/all of the learning media program can be reused to develop other learning media) 4 6 communicative (on target and acceptable to the target's wishes) 7 creative in ideas and pouring ideas 4 8 clarity of descriptions, discussions, examples, simulations and exercises 4 9 the suitability of the material with the learning objectives 4 10 audio (narration, sound effects, background, music) 3 11 clarity of descriptions, discussions, examples, simulations and exercises 4 12 layout interactive 3 based on table 1 and table 2 above, the calculation of each criterion is based on the media feasibility assessment guidelines. highest score = 5, and lowest score = 1 there are 4 desired classes, namely very good (sb), good (b), less good (kb) and not good (tb). range = largest data – smallest data = 5 – 1 = 4 interval length (p) = 0.5 based on the calculation above, it can be determined the range of scores and the criteria for the value as follows. criteria score range. a. 4.0 < score 5.0 very good b. 3.0 < score 4.0 good c. 2.0 < score 3.0 not good d. < score 2.0 not good the design of the articulate story learning media which has been assessed by experts and revised, is then tested on graphic engineering students with a sample of 15 students on a limited scale trial. student response data stated the acceptance of the media as an articulate story linebased learning media in the form of webhtml5 which can be used in a blended manner, namely online and offline. when it reaches a score of 2.51. student responses were taken using a questionnaire accompanied by criticism and suggestions as a revision guide given after learning 375 to use the media articulate stroy line 3.0. the results of student responses are shown in table 3. table 4. recapitulation of student responses on trials limited scale no response criteria score range students give feedback percentage (%) 1 very supportive 3,25 < score 4.00 10 66,66% 2 supportive 2,50 < score 3.25 5 33,33% 3 less supportive 1,75 < score 2.50 0 0 4 no supportive 1 < score 1.75 0 0 the number of students with very supportive and supportive criteria 15 100% based on table 2, students gave 100% "supportive" and "supportive" responses to the learning media using the aticulate story line 3.0. the number of respondents with a "strongly supportive" response is greater than the number of respondents with a "supportive" response. the description above explains that the learning media using aticulate story line 3.0 is well received because it reaches a score of 3.81. furthermore, to find out the average score of student responses, it can be seen in table 5. table 5. recapitulation of student responses on trials limited scale no response score mean criteria 1 interest in using media 3,27 very supportive 2 media according to learning objectives 3,47 very supportive 3 easy-to-operate media 3,07 supportive 4 media helps understanding the material 3,00 supportive 5 media can use online or offline 3,20 supportive 6 media with practice questions and new information 3,47 very supportive 7 media increases learning motivation 3,00 supportive 8 media is used indenpendently 3,47 very supportive 9 more effective and efficient media 3,27 very supportive 10 intersest in using media in other materials 3,33 very supportive the score for the ss answer (strongly agree) is 4 the score for the answer s (agree) is 3 the score for the ks answer (disagree) is 2 the score for the ts answer (disagree) is 1 material aspect total score = 34 average score = 2.88 criteria = very good aspects of expert media 1 total score = 34 average score = 2.88 criteria = very good expert media aspect 2 total score = 32 average score = 2.66 criteria = very good based on the ten response items that received the "very supportive" criteria, there were seven statements and 3 items with the "supporting" criteria. so that the learning media product using the aticulate story line 3.0 developed can be accepted by the respondents. conclusions and suggestions conclusion the first, that the development of blended e-learning applications using soft ware articulate story line 3.0 is very helpful in the process of implementing distance learning which can be done online or non-online and based on media tests and material tests concludes that blended e-learning application development with using articulate story line 3.0 software is feasible to use. the second, based on student responses, 90% strongly supports and 10% supports the application of blended e-learning application development using articulate story line 3.0 soft ware. suggestion it is hoped that this research will continue to develop and be used during the distance learning process that will be implemented. it is hoped that researchers can always upgrade any information about distance learning based on articulate story line 3.0. hopefully this research can be an opening in the implementation and development of articulate story-based learning media. references ardhana januar mahardhani, m. k. (2020). menjadi warga negara yang baik pada masa pandemi covid-19: persprektif kenormalan baru. jpk (jurnal pancasila dan kewarganegaraan), 5(2), 65–76. https://doi.org/10.24269/jpk.v5.n2.2020.p p65-76 arifin, r. w., septanto, h., & wignyowiyoto, i. (2018). pengembangan media pembelajaran berbasis video animasi dengan model addie 376 dalam kegiatan pembelajaran blended learning. information management for educators and professionals : journal of information management, 2(2), 179–188. retrieved from http://www.ejournalbinainsani.ac.id/index.php/imbi/article/vie w/946 darmawan, m. f., & nashoih, a. k. (2019). pengembangan mobile learning berbasis android pada mata pelajaran bahasa indonesia untuk mendukung pembelajaran blended learning. jurnal education and development, 7(4), 14. https://doi.org/10.37081/ed.v7i4.1315 ekayati, r. (2018). implementasi metode blended learning berbasis aplikasi edmodo. edutech: jurnal ilmu pendidikan dan ilmu sosial, 4(2), 50–56. https://doi.org/10.30596/edutech.v4i2.22 77 el iq bali, m. m., zamroni, umar, musthofa, b., sulistiani, i. r., dewi, m. s., … abdullah, d. (2021). the effect of quipper school assisted blended learning (qsbl) on student motivation and interest in learning. journal of physics: conference series, 1899(1), 012154. https://doi.org/10.1088/17426596/1899/1/012154 harahap, s. h. (2015). pemanfaatan e-learning berbasis lcms moodle sebagai media pembelajaran untuk mata kuliah sistem informasi akuntansi. jurnal riset akuntansi dan bisnis, 15(1), 86–99. https://doi.org/10.30596/jrab.v15i1.429 hikmah, n., saridewi, n., & agung, s. (2017). penerapan laboratorium virtual untuk meningkatkan pemahaman konsep siswa. educhemia (jurnal kimia dan pendidikan), 2(2), 186–195. https://doi.org/10.30870/educhemia.v2i2 .1608 janah, r., sukarelawati, s., & agustini, a. (2019). implementasi program pelibatan dan pemberdayaan masyarakat pt. tirta investama aqua babakan pari. jurnal komunikatio, 5(1), 7–10. https://doi.org/10.30997/jk.v5i1.1692 khoiroh, n., & anifah, l. (2017). pengaruh model pembelajaran blended learning dan motivasi belajar terhadap hasil belajar siswa kelas viii smpn 1 gumukmas. jurnal penelitian ilmu pendidikan, 10(2), 97–110. https://doi.org/10.21831/jpipfip.v10i2.139 86 murtikusuma, r. p., hobri, fatahillah, a., hussen, s., prasetyo, r. r., & alfarisi, m. a. (2019). development of blended learning based on google classroom with osing culture theme in mathematics learning. journal of physics: conference series, 1165(1), 012017. https://doi.org/10.1088/17426596/1165/1/012017 pantan, f., & benyamin, p. i. (2020). peran keluarga dalam pendidikan anak pada masa pandemi covid-19. kharismata: jurnal teologi pantekosta, 3(1), 13–24. https://doi.org/10.47167/kharis.v3i1.43 polhun, k., kramarenko, t., maloivan, m., & tomilina, a. (2021). shift from blended learning to distance one during the lockdown period using moodle: test control of students’ academic achievement and analysis of its results. journal of physics: conference series, 1840(1), 012053. kryvyi rih: iop publishing. https://doi.org/10.1088/17426596/1840/1/012053 rahmad, i. f., & fragastia, v. a. (2017). perancangan navigasi robot berbasis suara menggunakan android. seminar nasional informatika (snif), 1(1), 320–324. retrieved from http://ejournal.potensiutama.ac.id/ojs/index.php/snif/article/view /193/140 siregar, n., & manurung, s. l. (2020). pengaruh blended learning terhadap kreativitas mahasiswa calon guru di universitas negeri medan. edumatika : jurnal riset pendidikan matematika, 3(1), 44–51. https://doi.org/10.32939/ejrpm.v3i1.485 jurnal riset informatika vol. 1, no. 4 september 2019 p-issn: 2656-1743 e-issn: 2656-1735 205 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional perancangan dan penerapan metode weighted product dalam sistem pendukung keputusan pembelian laptop nur sumarsih program studi sistem informasi stmik nusa mandiri www.nusamandiri.ac.id nursumarsih8@gmail.com abstrak konsumen pada saat membeli laptop biasanya bertujuan sekedar mengerjakan pekerjaan sekolah atau kantor yang sebagian besar hanya untuk mengetik laporan atau mencari informasi lewat internet. pasar di indonesia sangat besar, sehingga berbagai merk dan jenis laptop yang tersedia saat ini dijual dengan harga yang bervariasi dan kompetitif, sehingga para calon pembeli menjadi tambah bingung untuk membeli. kebanyakan para pembeli, membeli laptop dengan spesifikasi yang tidak disesuaikan dengan kegunaannya. pendekatan yang digunakan untuk memecahkan masalah tersebut menggunakan metode weighted product. penelitian ini bertujuan untuk membantu konsumen dalam pemilihan laptop melalui kriteria-kriteria yang telah ditentukan. hasil perhitungan pemilihan laptop dengan metode weighted product yang didapat dengan hasil nilai tertinggi adalah laptop toshiba satellite c55 dan hasil terendah adalah laptop acer aspire e1-470. kata kunci: metode weighted product, pemilihan laptop, penunjang keputusan abstract consumers when buying a laptop usually aims just to do school or office work, mostly just to type reports or find information via the internet. the market in indonesia is very large, so that various brands and types of laptops available today are sold at varied and competitive prices, so potential buyers are even more confused about buying. most buyers, buy laptops with specifications that are not adapted for their use. the approach used to solve the problem uses the weighted product method. this study aims to assist consumers in choosing a laptop through predetermined criteria. the results of the calculation of the selection of laptops with the weighted product method obtained with the highest value is the toshiba satellite c55 laptop and the lowest result is the acer aspire e1-470 laptop. keywords: weighted product method, laptop selection, decision support pendahuluan pesatnya pasar laptop membuat para produsen saling berebut untuk menjadi pemimpin pasar laptop. dengan munculnya berbagai kompetitor membuat produsen berlomba-lomba memberikan produk terbaik kepada konsumen melalui produk yang mereka tawarkan, sehingga menimbulkan persaingan yang lebih kompetitif. biasanya konsumen membeli laptop hanya sekedar mengerjakan pekerjaan sekolah atau kantor yang sebagian besar hanya untuk mengetik laporan atau mencari informasi lewat internet, dengan kebutuan yang ada kita bisa membeli laptop yang berspesifikasi menengah. saat ini berbagai merk dan jenis laptop yang ada pasar indonesia, dijual dengan harga yang bervariasi dan kompetitif, sehingga para calon pembeli menjadi tambah bingung untuk memilihnya (khairina, ivando, & maharani, 2016), (saputra, sari, & mesran, 2017), dan kesulitan dalam menentukan pilihan (n. syafitri, syafitri, sutardi, & dewi, 2016) yang sesuai dengan kebutuhannya. banyak juga para pembeli, membeli laptop dengan spesifikasi yang tidak disesuaikan dengan kegunaannya (n. syafitri et al., 2016). terkadang konsumen, tentunya terkadang kita kesulitan dalam memilih laptop disesuaikan dengan anggaran yang ada. sesuai dengan permasalahan yang sudah dikemukakan diatas, pada penelitian yang penulis lakukan, menggunakan metode weighted product (wp), dikarenakan berdasarkan penelitian sebelumnya, yang dilakukan oleh syafitri (2016), memberikan solusi dari 5 (lima) laptop (n. a. syafitri, sutardi, & dewi, 2016) yang menjadi pilihan didapatkan akurasi yang baik dengan metode wp tersebut. begitu juga penelitian oleh rani (2014) dengan pemilihan sepeda motor http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 4 september 2019 206 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional dengan metode wp, menghasilkan hasil yang baik dalam pemilihan sepeda motor (rani, 2014). ruang lingkup pembahasannya dimulai dari menentukan kriteria yang dipakai dalam penelitian ini adalah harga, jenis processor, kapasias ram, hardisk, dan vga (video graphics accelerator), menentukan alternatif berupa laptop dengan beberapa merk, dan sistem ini akan menghasilkan penilaian pemilihan laptop yang nantinya akan menghasilkan ranking dari nilai terbesar ke terkecil. tujuan penelitian ini untuk membantu konsumen dalam pemilihan laptop melalui kriteriakriteria yang telah ditentukan. adanya sistem pendukung keputusan dengan metode weighted product ini konsumen dapat memilih laptop yang sesuai dengan kebutuhan. metode penelitian penelitian ini kriteria yang digunakan sebanyak 5 (lima) kriteria, yaitu : a. harga pada dasarnya adalah sebagai tolak ukur terpenting bagi sebagian besar calon pembeli. b. ram (random access memory) sebagai media penyimpanan temporer dalam sebuah computer, menjadi pertimbangan penting, dikarenakan ram sangat mempengaruhi kinerja dari sebuah computer. semakin besar kapasitas dan seamakin tinggi kecepatan dari ram sebuah laptop, semakin bagus dan cepat pula kinerja laptop tersebut. c. processor sebagai otak dari komputer merupakan salah satu pertimbangan penting dalam pemilihan laptop. processor dengan kecepatan yang inggi mempu memproses dan melakukan perhitungan dengan cepat pula. d. hardisk sebagai media penyimpanan semi-permanen menjadi pertimbangn penting, dimana semakin besar kapasitas harddisk sebuah laptop, semakin banyak pula data-data yang bisa disimpan oleh penggunanya. e. vga (video graphics accelerator) sebagai pengolah data grafis dalam sebuah laptop menjadi pertimbangan penting, khususnya bagi calon pembeli laptop yang bertujuan untuk menggunakan laptopnya sebagai media bermain game ataupun sebagai media bekerja yang menggunakan aplikasi-aplikasi multimedia yang berat. sedangkan untuk alternatif pilihan produk dari toko penjual laptop adalah sebagai berikut : a. acer aspire one z1402 b. lenovo s400 c. toshiba satellite c55 d. acer aspire e1-470 e. asus s46cb skala pengukuran yang digunakan dalam observasi kepada responden adalah skala likert, dimana akan didapat jawaban berupa sangat setuju, setuju, netral, tidak setuju, dan sangat tidak setuju. dalam penelitian ini analisa yang digunakan adalah analisis data kuantitatif, karena data yang didapat berupa simbol angka atau bilangan yang dapat menghasilkan suatu kesimpulan yang berlaku di dalam suatu parameter. metode weighted product (wp) metode weighted product menggunakan teknik perkalian untuk menghubungkan ratingattribute, dimana rating tiap atribut harus dipangkatkan terlebih dahulu dengan atribut bobot yang bersangkutan (kusumadewi, hartati, harjoko, & wardoyo, 2006). . dalam penelitian ini akan menggunakan metode weighted product dimana di dalam penentuan sebuah keputusan dengan cara perkalian untuk menghubungkan rating atribut, dimana rating setiap atribut dipangkatkan dulu dengan bobot atribut yang bersangkutan. langkah-langkah yang dilakukan dalam penyelesaian masalah menggunakan metode weighted product seperti dibawah ini. 1. normalisasi atau perbaikan bobot 𝑊𝑗 = 𝑊𝑗 ∑ 𝑤𝑗 ..................................................................... (1) melakukan normalisasi atau perbaikan bobot untuk menghasilkan nilai 𝑤𝑗 = 1 dimana 1, 2, …, n adalah banyak alternatif dan ∑ 𝑤𝑗 adalah jumlah keseluruhan nilai bobot. 2. menentukan nilai vektor (s) 𝑆𝑖 = ∏ 𝑋𝑖𝑗 𝑊𝑗 ∏ 𝑋𝑖𝑗 𝑊𝑗 𝑛 𝑗−1 𝑛 𝑗−1 ............................. (2) , dengan i = 1, 2, ..., n 3. menentukan nilai vector (s) dengan cara mengalikan seluruh kriteria dengan alternatif hasil normalisasi atau perbaikan bobot yang berpangkat positif untuk kriteria keuntungan (benefit) dan yang berpangkat negatif untuk kriteria biaya (cost). dimana (s) merupakan preferensi kriteria, (x) merupakan nilai kriteria dan (n) merupakan banyaknya kriteria. 4. menentukan nilai vektor (v) 𝑉𝑖 = ∏ 𝑥𝑖𝑗 𝑤𝑗 𝑛 𝑗=1 ∏ (𝑋𝑗 𝑤)𝑛𝑗=1 𝑤𝑗 .......................................................... (3) http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 4 september 2019 p-issn: 2656-1743 e-issn: 2656-1735 207 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional , dengan i = 1, 2, ..., n (3) menentukan nilai vector (v) dimana vector (v) merupakan preferensi alternatif yang akan digunakan untuk perangkingan dari masing-masing jumlah nilai vector (s) dengan jumlah seluruh nilai vector (s) . start input nilai aternatif, input kriteria (c), input kriteria, bobot (w) perbaikan bobot kriteria pemangkatan vektor s terhadap bobot kriteria vektor v proses alternatif keputusan output alternatif keputusan end gambar 1. algortima metode weighted product bobot kriteria tersebut yang dijadikan pengujian didapat dari hasil kuesioner dimana responden memilih tingkat kepentingan sesuai dengan kebutuhan yang sesuai dalam melakukan pemilihan laptop, kemudian dilakukan normalisasi bobot atau perbaikan bobot dengan menentukan vektor s yaitu nilai dari setiap alternatif, perhitungan ini dilakukan dimana data yang akan dikalikan yang sebelumnya dilakukan pemangkatan dengan bobot masing–masing kriteria. setelah masing–masing vektor s mendapatkan nilai langkah selanjutnya adalah menentukan nilai vektor v yang digunakan untuk perangkingan alternatif. setelah perhitungan menggunakan vektor v selesai, langkah selanjutnya adalah memasukan semua hasil perhitungan ke dalam tabel sesuai nilai tertinggi dari nilai vektor v, maka akan didapatkan hasil perhitungan yang menunjukkan perangkingan nilai vektor v yang terbesar hingga terkecil, sehingga didapat alternatif terbaik rekomendasi pemilihan laptop berdasarkan nilai tertinggi vektor v. hasil dan pembahasan a. data penelitian pada tahap ini penulis mengumpulkan data pemilihan laptop yang diperlukan dalam melakukan perhitungan menggunakan metode weighted product. berikut ini adalah kriteria yang dijadikan acuan dalam memilih laptop dengan menggunakan metode weighted product. tabel 1. kriteria kriteria simbol harga c1 ram c2 processor c3 hardisk c4 vga c5 dari tabel tersebut, maka ditentukan suatu tingkatan kepentingan kriteria berdasarkan nilai bobot pada setiap kriteria dengan nilai bobot 1 sampai dengan 5, pembobotan ini mengacu pada skala likert, yaitu: tabel 2. nilai bobot pernyataan bobot sangat tidak penting 1 tidak penting 2 cukup penting 3 penting 4 sangat penting 5 b. data pengujian pada tahap ini akan dilakukan pengujian dengan menggunakan metode weighted product untuk pengolahan data menentukan keputusan pemilihan laptop. 1. metode weighted product ada beberapa langkah untuk melakukan perhitungan menentukan keputusan pemilihan laptop dengan menggunakan metode weighted product adalah sebagai berikut. a. menentukan alternatif menentukan alternatif yang akan digunakan dalam perhitungan. pada pengujian ini akan digunakan 5 sampel data laptop. tabel 3. data laptop no laptop spesifikasi kode harga ram processor hdd vga 1 acer aspire one z1402 4.390.000 2gb intel core i3 500 gb intel hd 5.500 a 2 lenovo s400 3.900.000 4gb intel core i3 500 gb amd radeon hd 7450 b 3 toshiba satellite 6.390.000 4gb intel core i3 1tb intel hd c http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 4 september 2019 208 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional no laptop spesifikasi kode harga ram processor hdd vga c55 5.500 4 acer aspire e1-470 5.490.000 2gb intel core i3 500 gb intel hd 4000 d 5 asus s46cb 7.102.000 4gb intel core i3 500 gb nvidia geforce gt 740 e b. menentukan perbaikan bobot kriteria menetukan bobot preferensi atau menentukan tingkat kepentingan berdasarkan tingkat kepentingan masing-masing kriteria. berikut adalah nilai bobot yang diberikan oleh responden, yaitu: tabel 4. masukkan responden kriteria nilai harga 5 kapasitas ram 3 jenis processor 4 kapasitas hardisk 3 vga 2 selanjutnya akan dilakukan perbaikan bobot terlebih dahulu dengan bobot awal w= (5, 3, 4, 3, 2), dengan w adalah bobot masing-masing kriteria yang responden berikan. berikut adalah hasil dari perhitungan perbaikan bobot kriteria. tabel 5. perbaikan bobot kriteria kriteria nilai bobot harga 5 0,294 ram 3 0,176 processor 4 0,235 hardisk 3 0,176 vga 2 0,118 menentukan bobot setiap alternatif langkah selanjutnya adalah memberikan bobot kriteria untuk masing-masing data laptop yang terdapat pada tabel 3 data laptop. berikut adalah bobot kriteria setiap laptop, yaitu tabel 6. bobot kriteria setiap laptop kriteria alternatif a b c d e harga 4 5 3 4 3 ram 1 2 2 1 2 processor 5 5 5 5 5 hardisk 3 3 5 3 3 vga 3 3 3 2 5 menghitung vector s setelah mendapatkan perhitungan nilai perbaikan bobot kriteria, maka langkah berikutnya adalah menghitung vector s dimana perhitungan ini akan dikalikan tetapi sebelumnya dilakukan pemangkatan dengan bobot masing-masing kriteria. dengan bobot sebagai pangkat positif untuk kriteria yang menguntungkan dan bobot negatif untuk kriteria biaya. berikut adalah hasil dari perhitungan vector s, yaitu: tabel 7. perhitungan vector s alternatif bobot a 1,339 b 1,417 c 1,798 d 1,276 e 1,746 menentukan vector v setelah mendapatkan nilai vector s, langkah selanjutnya adalah menentukan perangkingan alternatif laptop dengan cara membagi nilai vector v yang digunakan untuk perankingan bagi setiap alternatif dengan nilai total dari semua nilai alternatif vector s. setelah perhitungan menggunakan vector v selesai, langkah selanjutnya adalah memasukkan semua hasil perhitungan ke dalam table sesuai nilai tertinggi dari vector v, maka akan didapat nilai tertinggi sebagai nilai rekomendasi. tabel 8. nilai hasil alternatif nilai a 0,176 b 0,187 c 0,237 d 0,168 e 0,230 maka hasil dari perhitungan pemilihan laptop dengan menggunakan metode weighted product menyatakan bahwa nilai tertinggi adalah alternatif c laptop toshiba satellite c55, kedua alternatif e laptop asus s46cb, ketiga alternatif b laptop lenovo s400, ke empat alternatif a laptop acer aspire one z1402 dan terendah adalah alternatif d laptop acer aspire e1-470. setelah dilakukan perhitungan secara manual, maka selanjutnya akan dilakukan perhitungan dengan menggunakan microsoft excel. berikut adalah perhitungan yang telah dilakukan, yaitu tabel 9. perbaikan bobot kriteria kriteria harga ram prosesor hardisk vga cost/benefit cost benefit benefit benefit benefit bobot 5 3 4 3 2 jumlah bobot 17 perbaikan bobot 0,2941 0,1765 0,23529 0,1765 0,1176 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 4 september 2019 p-issn: 2656-1743 e-issn: 2656-1735 209 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional pada tabel 9 diatas dapat dilihat bahwa nilai yang dihasilkan dengan menggunakan microsoft excel tidak jauh berbeda dengan hasil yang dilakukan dengan menggunakan perhitungan manual. tabel 10. perhitungan vector s alternatif / kriteria harga ram prosesor hardisk vga vector s acer aspire one z1402 4 1 5 3 3 1,34189 lenovo s400 5 2 5 3 3 1,42016 toshiba satellite c55 3 2 5 5 3 1,80608 acer aspire e1 470 4 1 5 3 2 1,27938 asus s46cb 3 2 5 3 5 1,75261 selanjutnya hasil dari perhitungan vector s hasilnya pun tidak jauh berbeda dengan hasil yang dilakukan dengan perhitungan manual. tabel 11. perhitungan vector v alternatif vector v acer aspire one z1402 0,1766 lenovo s400 0,1869 toshiba satellite c55 0,2376 acer aspire e1 470 0,1683 asus s46cb 0,2306 berdasarkan perhitungan dengan microsoft excel, maka hasil yang didapat sama dengan perhitungan secara manual dimana nilai tertinggi adalah alternatif c laptop toshiba satellite c55, kedua alternatif e laptop asus s46cb, ketiga alternatif b laptop lenovo s400, ke empat alternatif a laptop acer aspire one z1402 dan terendah adalah alternatif d laptop acer aspire e1-470. gambar 1. grafik hasil nilai perhitungan weighted product kesimpulan untuk menggunakan metode weighted product dibutuhkan kriteria yang akan dijadikan pertimbangan, kriteria yang telah ditentukan adalah harga, kapasitas ram, jenis processor, kapasitas hardisk, dan vga. membangun sistem pendukung keputusan pemilihan laptop menggunakan metode weighted product, langkah pertama yang dilakukan adalah menentukan kriteria dan alternatif laptop yang akan dibandingkan, kemudian data terebut akan dihitung dengan menggunakan metode weighted product. hasil perhitungan pemilihan laptop dengan metode weighted product yang didapat dengan hasil nilai tertinggi adalah laptop toshiba satellite c55 dan hasil terendah adalah laptop acer aspire e1-470. daftar referensi khairina, d. m., ivando, d., & maharani, s. (2016). implementasi metode weighted product untuk aplikasi pemilihan smartphone android. jurnal infotel, 8(1), 16–23. retrieved from http://ejournal.st3telkom.ac.id/index.php/in fotel/article/view/47 kusumadewi, s., hartati, s., harjoko, a., & wardoyo, r. (2006). fuzzy multi-attribute decision making (fuzzy madm). yogyakarta: graha ilmu. rani, s. (2014). sistem pendukung keputusan pemilihan sepeda motor berbasis webdengan metode weighted product. pelita informatika budi darma, 7(3), 62–66. saputra, i., sari, s. i., & mesran, m. (2017). penerapan elimination and choice translation reality (electre) dalam penentuan kulkas terbaik. komik (konferensi nasional teknologi informasi dan komputer), 1(1), 295–305. https://doi.org/10.30865/komik.v1i1.512 syafitri, n. a., sutardi, s., & dewi, a. p. (2016). penerapan metode weighted product dalam sistem pendukung keputusan pemilihan laptop berbasis web. semantik, 2(1), 169–176. retrieved from http://ojs.uho.ac.id/index.php/semantik/arti cle/view/762 syafitri, n., syafitri, n. a., sutardi, s., & dewi, a. p. 0 0,05 0,1 0,15 0,2 0,25 acer aspire one z1402 lenovo s400 toshiba satellite c55 acer aspire e1 470 asus s46cb http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 1, no. 4 september 2019 210 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional (2016). penerapan metode weighted product dalam sistem pendukung keputusan pemilihan laptop berbasis web. semantik, 2(1), 169–176. retrieved from http://ojs.uho.ac.id/index.php/semantik/arti cle/view/762 http://creativecommons.org/licenses/by-nc/4.0/ 149 implementation of electronic customer relationship management in the donation service information system ali ibrahim1*), beriadi agung nur rezqeb2 *1,2department of information systems faculty of computer science, universitas sriwijaya, indonesia *1,2management of information systems and business (misab) research group, faculty of computer universitas sriwijaya, indonesia. *1,2multimedia and game programming laboratory faculty of computer universitas sriwijaya, indonesia https://unsri.ac.id/ aliibrahim@unsri.ac.id*1, beriadiberlix@gmail.com2 (*)corresponding author abstrak laznas lmi kanwil sumsel merupakan lembaga yang bergerak di bidang agama dan kemanusiaan. salah satu layanan yang diberikan oleh kanwil lmi sumsel adalah layanan donasi. namun, pelayanan tersebut masih belum efektif dan efisien. berdasarkan hasil kuisioner pelayanan donasi pada lmi kanwil sumsel didapatkan hasil perhitungan. diperoleh net promoter score1 sebesar -61,6% yang menunjukkan nilai negatif. hal ini menunjukkan perlunya peningkatan pelayanan donasi agar tercipta loyalitas. konsep e-crm bertujuan untuk memberikan kepuasan dan meningkatkan loyalitas. oleh karena itu diperlukan suatu sistem informasi pelayanan donasi yang dapat mempermudah baik lmi maupun donatur. serta pengukuran yang mengukur loyalitas donatur dengan menggunakan metode perhitungan net promoter score dan metode pengembangan sistem fast. dari hasil pengukuran net promoter score2 didapatkan hasil perhitungan sebesar 77 % hal ini menunjukkan bahwa loyalitas donatur mengalami peningkatan terhadap peningkatan pelayanan donasi di lmi kanwil sumsel. keywords: dona, e-crm, fast, lmi, net promoter score abstract laznas lmi regional office of south sumatra is an institution engaged in the field of religion and humanity. one of the services provided by the lmi regional office of south sumatra is a donation service. however, the service is still not effective and efficient. based on the results of the questionnaire on donation services at the lmi regional office of south sumatra, the calculation results. obtained net promoter score1 of -61.6% which indicates a negative value. this shows the need to improve donation services in order to create loyalty. the ecrm concept aims to provide satisfaction and increase loyalty. therefore we need a donation service information system that can make it easier for both lmi and donors. as well as a measurement that measures the loyalty of donors using the net promoter score calculation method and the fast system development method. from the measurement results of net promoter score2, the calculation results are 77%, this shows that the loyalty of donors has increased towards the improvement of donation services at lmi regional office of south sumatra. keywords: donation, e-crm, fast, lmi, net promoter score introduction donation or donation or charity is a gift that is generally physical in nature by individuals or legal entities. this giving has a voluntary nature without any benefit in nature, although the donation can be in the form of food, goods, clothing, toys or vehicles but this is not always the case, in the event of a disaster emergency or in certain other circumstances (dewantry, budiwati, & sanjaya, 2015). donation activities are generally found around roads and places where natural disasters are occurring. the results of the donation are given to someone or to an agency that needs the donation. someone who donates is also called a donor. in a national zakat institution, donation is one of the programs contained in the national zakat institution. like in lmi, baznas, dompet dhuafa and others. almost in every city in indonesia there are branches or representative offices respectively. where each branch or representative office of zakat institutions has a donation program that must be carried out and achieved every year. like one of them in south sumatra, namely the infaq management institute (lmi), lmi has one of the mailto:aliibrahim@unsri.ac.id*1 150 programs, namely donation, in which the donation focuses on the south sumatra region. trust and ease of donation are the most important things that must be considered. the trust of donors has made the donation program continue to this day. donor loyalty is a very important aspect as a place to manage these donations. besides being able to make a donor a regular donor. donor loyalty can strengthen the relationship between lmi and the donors themselves. for now, every donor who donates will be given a small magazine as a form of gratitude for donating at lmi. the continuation of the donation program depends on the perception of donors who trust the institution. therefore, lmi must be able to create an effective and efficient donation service, so that donors will have a good perception of the institution that manages the donation, and later will be able to become loyal donors. in the donation service process at lmi, there are currently three ways to donate. the first way donors must come directly to lmi's place, the second way donors must first fill in their bio in the google forms listed on the lmi website then donors can donate. the third way is that lmi will pick up donations. this process is less effective and efficient. therefore, lmi must be able to provide effective and efficient services to donors in order to create a good relationship between donors and lmi. for that we need the right way so that lmi becomes a place to donate that knows its donors very well, so that donors become loyal to donate at lmi. the best way to build relationships with donors is to build customer relationship management (crm). customer relationship management (crm) is a customer-oriented business strategy in which a company tries to increase customer satisfaction and loyalty by offering services through several specific programs to customers (tanjungsewu paribhasagita & lisnawati, 2016). electronic customer relationship management (e-crm) is a form of it application in the crm field of a company by utilizing internet technology. by using e-crm, lmi can provide the best service to donors and can build better relationships with donors. the method used to measure customer loyalty is the net promoter score method. the net promoter score method was developed by fred reichheld of harvard. the net promoter score (nps) is a model the measurement of loyalty is very simple. based on the results of the questionnaire on donation services at the lmi regional office of south sumatra, the calculation results are net promoter score1 of -61.6% which shows a negative value. this shows that there is a need for innovation and service improvement so as to create loyalty from donors in a study conducted by rahayu and irawan, in this study researchers designed an ecrm system to improve service and loyalty in kumon educational institutions. this research produced an e-crm prototype which has main features, namely promotion, registration, payment, score lists, learning evaluations, announcements, and complaint handling thereby increasing loyalty and customer service to kumon educational institutions (rahayu & irawan, 2019). other research nikou (nikou, harihodin bin selamat, yusoff, & khiabani, 2016) how the role of e-crm in increasing customer loyalty provides useful insights for service industry managers to implement e-crm in its best form and adapt it to their organizational or industry culture to increase customer loyalty levels and get more profit and revenue for their own business. other research by huseynov and amazhanova (aldaihani & ali, 2018) the impact of e-crm features on customer satisfaction and perceived utility as a mediating variable in the turkish e-commerce sector is investigated in this study. quantitative research methodologies were used in this study. self-managed likert-type online surveys were used to obtain primary data from 210 respondents. customer satisfaction is impacted directly and indirectly (through perceived usefulness characteristics) by the e-crm elements studied in this study (complaint management, communication, information content, security, and privacy). (aldaihani & ali, 2018). in another study by bezhovski (bezovski & hussain, 2016), which identifies and describes the benefits of using this advanced technology in the banking sector and helps banks make the right decisions regarding the implementation and / or further improvement of existing e-crm. the results of the study found that e-crm has reduced workload at branches, lowered administrative costs, increased cross selling, bank revenue and enabled bankers to analyze customer needs by having access to all past transactions. echannels have improved information dissemination and allowed management to introduce new products and schemes more quickly (bezovski & hussain, 2016). other research conducted by ali ibrahim et al, (ibrahim et al., 2019) the problems faced by the fasilkom canteen related to customers can be overcome with the customer relationship management (crm) model. the method used is the crm scorecard. the number of respondents to the questionnaire was 59 people consisting of fasilkom students from the 2013-2016 class. these findings will provide future evaluations for the canteen facilitators in managing customers (ibrahim et al., 2019). in the benefits of implementing crm, the 151 data validation process in social media is of concern. because one of the important things in the implementation of social crm is the data the objective of this study is to show the results of research on current social crm together see the problem this time and provide a solution (ibrahim, ermatita, saparudin, & adetya, 2018). and other research conducted by asmara and ratnasari (asmara, 2016), this study measures visitor satisfaction and visitor loyalty in cave tourism by using the net promoter score calculation. from the measurement results, the level of visitor loyalty is very low, which is -13%. that is, it is likely that visitors will move to other tourist attractions. other research which is conducted korneta (korneta, 2018) researchers verified the effect of nps on growth and profitability of transport companies in poland. this goal is achieved by using the spearman rank correlation and linear regression. other research conducted by rajasekaran and dinesh (rajasekaran & dinesh, 2018) in this research, researchers research on how the net promoter score and how the customers rate your company using the net promoter score. other research conducted by dash (dash, 2018) this study examines nps in measuring customer loyalty. in another study by stander (stander, 2016), in order to assess the empirical accuracy of this indicator, nps was assessed in the context of professional football customer behavior in south africa. measurement and structural models are evaluated with a defined direct path between nps and consumer spending, as well as an indirect pathway with nps postulated as a mediator to activate purchasing behavior in nomological networks that include consumption motives traditional sports, using the theoretical context of loyalty-based business models and relationship marketing as points of departure. the survey included 2465 adult fans from one of the most popular and well-known professional football clubs in the country. nps is a direct predictor of consumer expenditure, according to the results of this study. it also shows that nps can act as a buffer between sports consumption motivations and spending. the findings of the study are examined, and future suggestions are suggested. (stander, 2016). according to buttle (buttle, 2007) customer relationship management or customer relationship management (crm) is a deep core strategy integrating internal processes and functions with the network external to create and deliver value for consumers profitable advice. meanwhile, according to brown and rigby, reincheld, dawson in vanessa (gaffar, 2007) reveals crm is the process of obtaining, sustaining, and developing profitable services, and it necessitates a laser-like concentration on the characteristics of a service that will generate client loyalty. (gaffar, 2007). e-crm is an electronic crm that uses a web browser, the internet, and other electronic media such as email, call centers, and personalization to deploy. e-crm is often referred to as e-service. (turban, chung, lee, & chung, 1999). the sustainability of the company depends on the company's ability to maintain its customers so that their customers can be loyal to the company and do not move with other companies. having loyal customers is an important asset that must be maintained by the company so that the company can continue to compete with other competitors. according to kotler and keller (kotler & keller, 2007) the following is a definition of client loyalty: despite situational variables and marketing efforts having the ability to trigger switching behavior, a strong desire to repurchase or repatronize a preferred product or service in the future. . an information system is a collection of people, data, procedures, and information technology (it) that work together to collect, process, store, and provide the information needed to run a business. (whitten, bentley, & dittman, 2004). the information system receives data input and instructions, processes the data with instructions and produces results. the basic system model of input, processing and output is suitable for simple processing systems (b.davis, 1992). research methods a. systems development method this research system development method is the fast (framework for the application of systems techniques) system development method because fast has a good standard and a planned process. in addition, the fast method is suitable for implementation in the scope of small and large projects (whitten et al., 2004). 152 fig 1. fast system development method (whitten et al., 2004) in fig 1. fast defines the stages to identify and observe problems, opportunities, obstacles, and hopefully what is expected to happen repair repair. this development is lifecycle because after completion implementation of implementation and maintenance then the system will provide feedback to the system analysis that has been designed. so that the stages the development above is continuously carried out for the improvement of the system. b. net promoter score in this research method there is also a measurement of donor loyalty with the number of respondents who will be measured 10-15 respondents. which of these respondents will be measured loyalty using a simple loyalty measurement net promoter score. the net promoter score (nps) method is a very simple but easy to understand and effective method for measuring the level of loyalty, so this method is widely used. using a scale of 0-10 and then dividing the customers who took the survey into three groups based on their answers. nps is the percentage of promoters minus the percentage of detractors presented in an easy to understand way, as well as the most effective short summary of how a company is doing (f. f. reichheld & covey, 2006). in nps, the types of customers are divided into: 1. promoters of customers who are enthusiastic about your product and will continue to buy. they will be happy to refer your product to others. promoters are also defined as those who give a score of 9 or 10. 2. passives customers who are satisfied with your product but not enthusiastic and may at any time move to another product if they find a more attractive deal. their passives that give them a 7 or 8. 3. customer detractors who have had a bad experience with our products and if the opportunity arises they will spread negative news about our products (negative word of mouth). customers usually give a value of only 0 to 6. fig. 2. classification of respondents net promoter score (f. reichheld, 2011) figure 2. explains the classification of respondents and how to calculate the net promoter score. c. crm phase according to robinson and kalakota (2001) there are three stages in the crm phase, namely getting new customers (acquire), improving customer relationships (enhance), and retaining customers (rertain). table 1 describes the three crm phases that will be applied to the donation service system at laznas lmi regional office of south sumatra (kalakota & robinson, 2001). table 1. crm phase no crm phase solution offered 1 acquire phase (get new customers) donation service information interesting and accurate that later will attract interest in donating. ease of service process donations for 153 no crm phase solution offered donors user built systems friendly 2 enhance phase (increase relationship with customers) there is login access for each donor. there is customer service make it easy for donors to communicate with lmi. there is a means of conveying criticism and suggestions 3 retain phase (maintain customer) there is a response to criticism and suggestions which has been given. there is documentation of evidence donation distribution of donations there is a page for donors to see donations that have been made paid, unpaid donations table. 1. describes the crm phases in the donation service system that will be implemented into the system. d. old system process analysis the old system process is currently running in the donation service process. fig 3. dfd level 0 old system figure 3. explains the old system process for donation fig. 3. explains services at laznas lmi regional office of south. e. dfd level 0 new system fig 4. dfd level 0 new system figure 4. describes the flow of the proposed system. there are 3 entities that use the system, namely admin, donors, and leader. admin can login to enter the system and manage user data, donation data, data donation transactions, faq data, criticism and suggestions data, documentation data donations and chat online. donors can view donation data and faq as well as processing donation transactions, donation confirmation, criticism and suggestions, as well as online chat. leaders can come inside system and view donor data, donation data, and donation transaction data and print reports. f. dfd level 1 as for dfd level 1 in the new system, there are 5 processes of registration, login, donation, customer service and also print reports. 154 fig. 5 dfd level 1 figure 5. describes the process for the donation service. in the donation service, there are 5 processes, namely the list process, the login process, the donation process, customer service and print reports. results and discussion a. results the final stage of this research is to produce a donation service information system by implementing e-crm and measuring the loyalty of donors using the net promoter score calculation method. in this system there are 3 system users, namely admin, leadership and also donors. b. discussion this discussion section will discuss the results of the system software that has been developed. the discussion will be divided based on the use of a system where there are admins, leaders and donors. here's the discussion system software in detail. admin page is a page for admins who are logged in and have entered the system. pages displayed according to rights admin access that is able to manage donations, donors, donation transactions, donation confirmation, donation documentation, faq, criticism and suggestions, and users. fig. 6 admin page figure 6. describes the admin page contained in the donation service system. this leadership page is a page for leaders who are logged in and have entered the system. the page displayed corresponds to management access rights, namely being able to view donation data and print it, view donor data and print it, view donation transaction data and print it out. fig. 7 describes the leader's page contained in the donation service system 155 this donor page is a page for donors to interact with the donation service system. the pages on the donor are dashboard, list of donors, homepage, about, faq, donation, donation details, continue donating, continue payment and confirm donations. fig 8. donors page figure 8. describes the donor page contained in the donation service system. c. calculation of the net promoter score researchers have distributed questionnaires that were filled in by 13 donors. from the results of this questionnaire, the score for the nps1 questions was obtained. from the results of the nps questions on the first questionnaire, the promoters, passives and detractors were grouped below. nps1 = %promoters — %detractors = 15.4% 77% = 61.6% after the new system was implemented, the second questionnaire was distributed. from the results of the nps questions on the second questionnaire, the promoters, passives, and detractors were grouped below. nps2 = %promoters — %detractors = 77% 0% = 77% from the results of the calculation of nps2 there is an increase from the first negative and the second result is positive. from the results of nps2 it can be concluded that the donors are loyal to the improvement of the donation service system for laznas kanwil south sumatra. in terms of arrangement and content, the results section and the subsequent discussion part provide the most flexibility. in general, the unadulterated, uninterpreted results should be presented first. the raw data or the findings after applying the strategies indicated in the methods section should be presented in these results. the outcomes are just that: outcomes; they don't draw any conclusions. the major goal of the results section is to offer the study's data so that other researchers can form their own conclusions and fully comprehend the reasoning behind them. a popular approach for the results section is to offer a series of figures followed by a detailed description of the figures in the text. a well-written results section includes clear figures and concise language. the numbers should substantiate the claims made in the paper or provide new insights. results should be presented in terms of non-dimensional variables whenever possible. conclusions based on the results of the research conducted and the results of the discussion previously described, the following conclusions can be drawn: with an increase in donation services at laznas lmi regional office of south sumatra, it can make it easier for lmi parties and also donors donate. by implementing e-crm in this donation service information system, donors will be more loyal to lmi. from the results of the distribution of the first questionnaire, it was found that nps1 showed a calculation result of -61.6%, this indicates that donors were not loyal to the donation services provided. after developing new systems and innovations, the second questionnaire was distributed, it was found that nps2 showed a 77% calculation. it can be concluded that the donors were very loyal with the increase in donation services at laznas lmi regional office of south sumatra. references aldaihani, f. m. f., & ali, n. a. bin. (2018). impact of electronic customer relationship management on customers satisfaction of the five stars hotels in kuwait. global journal of management and business research, 18(5-e), 1–11. retrieved from https://journalofbusiness.org/index.php/gj mbr/article/view/2564/ asmara, y. (2016). analisis kepuasan dan loyalitas pengunjung terhadap pelayanan di kawasan wisata goa selomangleng kota kediri dengan pendekatan structural equation modeling (institut teknologi sepuluh nopember). institut teknologi sepuluh nopember. retrieved from 156 https://repository.its.ac.id/62744/1/131210 0097-undergradute thesis.pdf b.davis, g. (1992). sistem informasi manajemen : kerangka dasar (a. s. adiwardana & b. widyahartono, eds.). jakarta: pt pustaka binaman pressindo. bezovski, z., & hussain, f. (2016). the benefits of the electronic customer relationship management to the banks and their customers. research journal of finance and accounting, 7(4), 112–116. retrieved from https://iiste.org/journals/index.php/rjfa/a rticle/view/28978 buttle, f. (2007). customer relationship management concepts and tools (1st ed.). malang: bayumedia publishing. dash, s. k. (2018). net promoter score-a metrics must for marketers. international journal of management, technology and engineering, 8(78), 78–83. dewantry, z. w., budiwati, s. d., & sanjaya, m. b. (2015). aplikasi pengelolaan dana donasi untuk penderita kanker (studi kasus: yayasan kanker indonesia). eproceedings of applied science, 1(3), 1786–1793. retrieved from https://openlibrarypublications.telkomunive rsity.ac.id/index.php/appliedscience/article/ view/4282 gaffar, v. (2007). crm dan mpr hotel (customer relationship management and marketing public relations). bandung: alfabeta. ibrahim, a., ermatita, saparudin, & adetya, z. (2018). analysis of weakness of data validation from social crm. proceedings of 2017 international conference on data and software engineering, icodse 2017, 2018january, 1–5. https://doi.org/10.1109/icodse.2017.8285 849 ibrahim, a., pratiwi, a., meytri, d. i., madri, kurniawan, m. a., & yuniarti, n. (2019). measuring customer satisfaction using crm scorecard in canteen fasilkom unsri. proceedings of 2018 international conference on electrical engineering and computer science, icecos 2018, 403–408. https://doi.org/10.1109/icecos.2018.86052 53 kalakota, r., & robinson, m. (2001). e-business 2.0: roadmap for success. boston, ma: addisonwesley professional. korneta, p. (2018). net promoter score, growth, and profitability of transportation companies. international journal of management and economics, 54(2), 136–148. https://doi.org/10.2478/ijme-2018-0013 kotler, p., & keller, k. l. (2007). manajemen pemasaran. jakarta: index. nikou, s. h., harihodin bin selamat, yusoff, r. c. m., & khiabani, m. m. (2016). electronic customer relationship management, customer satisfaction, and customer loyalty: a comprehensive review study. economics, international journal of management and invention, 2(12), 1133–1144. retrieved from http://www.rajournals.in/index.php/ijmei/a rticle/view/190 rahayu, f., & irawan, h. (2019). perancangan sistem electronic customer relationship management (e-crm) guna membantu meningkatkan pelayanan dan loyalitas pelanggan studi kasus: lembaga pendidikan kumon. idealis: indonesia journal information system, 2(4), 205–212. retrieved from https://jom.fti.budiluhur.ac.id/index.php/id ealis/article/view/1351 rajasekaran, m. n., & dinesh, m. n. (2018). how net promoter score relates to organizational growth. international journal of creative research thoughts, 6(2), 2320–2882. retrieved from www.ijcrt.orgwww.ijcrt.org reichheld, f. (2011). the ultimate question 2.0 (revised and expanded edition): how net promoter companies thrive in a customerdriven world (revised). boston, ma: harvard business review press. reichheld, f. f., & covey, s. r. (2006). the ultimate question: driving good profits and true growth (1st ed.). boston, ma: boston: harvard business school press. retrieved from 9781591397830 stander, f. w. (2016). a case for loyalty-based relational business models : assessing direct – and mediating effects of the net promoter score ( nps ) metric in commercial football consumption decisions. african journal of hospitality, tourism and leisure, 5(4), 1–16. tanjungsewu paribhasagita, & lisnawati, l. (2016). pengaruh customer relationship management terhadap loyalitas (survei pada nasabah asuransi jiwa prudentual nasabah cabang kota bandung). journal of business management education (jbme), 1(1), 39–55. https://doi.org/10.17509/jbme.v1i1.2277 turban, e., chung, h. m., lee, j. k., & chung, m. (1999). electronic commerce: a managerial perspective (1, ed.). hoboken: prentice hall. whitten, j. l., bentley, l. d., & dittman, k. c. (2004). metode desain & analisis sistem (6th ed.). yogyakarta: penerbit andi. jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 37 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional implementasi sistem informasi pemesanan jasa pengiriman barang kargo pada pt.suksema abadi logistik dengan model waterfall ahmad sinnun, intan ayu putri program studi rekaya perangkat lunak1, program studi sistem informasi2, fakultas teknik dan informatika universitas bina sarana informatika ahmad.sinnun@gmail.com1 ; intanayuputri4@gmail.com2 ; abstrak pt. suksema abadi logistik merupakan perusahaan jasa pengiriman barang untuk solusi b2b (bsinis to bisnis) di indonesia. belum adanya sistem informasi, penanganan order masih menggunakan sambungan telepon dan surat electronik yang digunakan pada perusahaan sehingga menjadikan adanya kendala dalam mencatat order pengiriman, monitoring penjadwalan armada, dan laporang status pengiriman yang tidak uptodate. penelitian ini bertujuan untuk menghasilkan perancangan dan implementasi sistem informasi untuk mendorong produktifitas dan pencatatan bisnis proses yang meliputi proses pemesanan, proses transaksi dan proses pengiriman yang bertujuan untuk memudahkan perusahaan pemesan jasa pengiriman melakukan order jasa, memantau jadwal pelaksanaan pengiriman dan mendokumentasikan proses pengiriman dengan dokumen yang terintegrasi. dengan mengimplementasikan metode pengembangan perangkat lunak berbasis metode waterfall, sistem informasi meliputi tiga akses untuk administrator, pelanggan, dan sopir. sistem informasi dapat memperlancar pemesanan jasa ekpedisi dan lebih terdokumentasi dengan data integrasi. kata kunci: sistem informasi, logistik, waterfall abstract pt. suksema abadi logistics is a freight services company for b2b solutions (bsinis to bisnis) in indonesia. the absence of information systems, the handling of orders still using telephone and electronic mail connection used in the company so as to make an obstacle in recording orders delivery, monitoring fleet scheduling, and laporang-status delivery that is not uptodate. this research aims to produce the design and implementation of information systems to encourage productivity and process business records that include the ordering process, transaction process and delivery process that aims to facilitate the company's customer service buyer, monitoring the delivery schedule and documenting the shipping process with integrated documents. by implementing software development methods based on waterfall method, information systems include three access for administrators, customers, and drivers. keywords: information systems, logistics, waterfall pendahuluan sistem informasi merupakan satuan komponen yang saling berhubungan dalam mengumpulkan, memproses, menyimpan dan mendistribusikan informasi (frieyadie, 2014). hal tersebut untuk mendukung pengambilan keputusan dan kendali serta memainkan aturan penting dalam organisasi. rabiatul (2015:181). dalam dunia ekspedisi sebuah perusahaan yang bergerak dalam bidang pengiriman barang semakin pesat pertumbuhannya (hidayat, 2014), banyaknya permintaan client dalam jasa pengiriman membuat seluruh perusahaan dalam bidang ini bersaing untuk memberikan pelayanan terbaik kepada pelanggannya. pt. suksema abadi logistik adalah salah satu perusahaan yang bergerak di bidang jasa pengiriman barang dan fokus pada solusi b2b. perusahaan ini menerima pesanan pengiriman barang dalam skala besar. pelanggan akan melakukan pemesanan yang selanjutnya bagian admin akan mengecek ketersediaan armada. jika armada tersedia, barang yang akan di kirim akan diambil ke tempat pelanggan. jika armada tidak tersedia, pesanan akan ditunda atau dibatalkan sesuai dengan permintaan pelanggan. sebelum adanya sistem informasi yang digunakan pada perusahaan tersebut. proses order armada dari http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 38 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional pelanggan melalui sambungan telepon atau surat electronik, pada saat menjawab telepon petugas administrasi yang menangani order harus mencocokan dokumen armada yang kosong dan jadwal pengiriman hal ini sangat rentan adanya data crash dengan jumlah armada yang mencapai lebih dari 100 unit. melihat permasalahan diatas penelitian ini mewujudkan pada perancangan dan implementasi sistem informasi untuk mendorong produktifitas dan pencatatan bisnis proses (fatayat & frieyadie, 2019) yang meliputi proses pemesanan, proses transaksi dan proses pengiriman yang bertujuan untuk memudahkan perusahaan pemesan jasa pengiriman melakukan order jasa, memantau jadwal pelaksanaan pengiriman dan mendokumentasikan proses pengiriman dengan dokumen yang terintegrasi. metode penelitian jenis penelitian penelitian ini menggunakan metode penelian teknik deskriptif, yakni metode yang digunakan untuk meneliti suatu objek, suatu set kondisi, suatu sistem pemikiran, ataupun suatu kelas peristiwa pada masa sekarang (saifudin & ardani, 2017). metode yang digunakan dalam pengembangan perangkat lunak dalam penelitian ini adalah model waterfall, metode ini melakukan pendekatan secara sistematis dalam proses pengerjaan system (palasara, sinnun, & tabrani, 2018). dengan kata lain metode ini tidak berfokus pada satu tahapan tertentu. tahapan dalam model waterfall ini mencakup tahap analisa kebutuhan perangkat lunak, desain, pembuatan kode program, dan pengujian (kendall & kendall, 2010). waktu dan tempat penelitian penelitian ini dilakukan pada tahun 2019 di pt. suksema abadi logistik. target/subjek penelitian target penelitian dengan metode deskriptif dalam melihat object proses bisnis pada pt. suksema abadi logistik dengan subject penelitian pada bagian pemesanan jasa, pencatatan transaksi pembayaran dan penjadwalan pengiriman. prosedur prosedur penelitian yang digunakan sebagaimana yang telah diuraikan pada bagian jenis penelitian mengikuti tahapan model waterfall sebagai berikut. 1. analisis kebutuhan perangkat lunak analisis kebutuhan berfokus pada kebutuhan sistem informasi mulai dari proses pemesanan jasa, proses pembayaran jasa, dan proses penjadwalan jasa. 2. desain tahapan ini mencakup rancangan basis data, pemodelan rancangan menggunakan unified modeling language (uml), dan rancangan tampilan antar muka. 3. implementasi pengkodean (coding) program menggunakan sublime text sebagai web editor bahasa pemrograman hypertext preprocessor (php) berdasarkan logika yang dirancang pada tahapan desain. teknik pengumpulan data teknik pengumpulan data berfungsi sebagai cara untuk mengumpulkan data dari suatu penelitian (saifudin & ardani, 2017). teknik pengumpulan data yang digunakan, terdiri dari observasi, wawancara dan studi pustaka. adapun penjelasan dari teknik pengumpulan data yang digunakan, diuraikan sebagai berikut: 1. observasi penulis melakukan observasi langsung ke pt. suksema abadi logistik untuk mengamati secara langsung proses pemesanan jasa ekspedisi, transaksi pembayaran, dan penjadwalan armada ekspedisinya. 2. wawancara wawancara merupakan proses tanya jawab langsung dan sistematis dengan karyawan pelaksana dilingkungan pt. suksema abadi logistik. hasil penelitian dan pembahasan a. analisis kebutuhan software a1. skenario kebutuhan admin mengelola data armada; mengelola data pelanggan; mengelola data vendor; mengelola data sopir; mengelola data kota; mengelola data pemesanan; mengelola data laporan pemesanan a2. skenario kebutuhan pelanggan melakukan daftar akun; melihat informasi armada; melakukan pemesanan armada; melihat riwayat pemesanan armada a3. skenario kebutuhan sopir melihat jadwal pengiriman; mengelola status pengiriman analisis kebutuhan sistem 1. admin, pelanggan, dan sopir melakukan login terlebih dahulu untuk dapat mengakses aplikasi ini dengan memasukkan username dan password. http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 39 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional 2. admin, pelanggan dan sopir melakukan logout setelah selesai menggunakan aplikasi. 3. sistem melakukan pengelolaan data armada, mengelola data sopir, mengelola data pelanggan, mengelola data pemesanan dan melihat laporan pemesanan. b. desain sebelum kode-kode program dibuat langkah selanjutnya penulis merancang dengan gambaran awal dengan use case diagram, aktivity diagram dan entity relation diagram (palasara et al., 2018). model entity relationalship menjelaskan hubungan antar data dalam basis data berdasarkan suatu persepsi object-object dasar yang mempunyai hubungan atau relasi antar objectobject tersebut (tabrani, kholil, & sinnun, 2019). use case diagram gambar 1 diagram use case sistem informasi ekspedisi barang tabel 1. deskripsi use case diagram sistem informasi ekspedisi barang use case narative sistem ekspedisi barang tujuan bagian administrator, pelanggan, sopir armada dapat mengakses dan mengelola data yang ada pada system informasi ekspedisi barang deskripsi aplikasi ini dapat di akses oleh administrator untuk mengelola data armada, pelanggan, vendor, sopir, kota, pemesanan, laporan pemesanan. sedangkan pelanggan dapat melakukan daftar akun, melihat informasi armada, melakukan pemesanan armada, melihat riwayat pemesanan armada. aplikasi ini juga memberikan fasilitas kepada sopir untuk melihat jadwal pengiriman dan mengelola status pengiriman skenario utama aktor administrator, pelanggan, sopir armada kondisi awal administrator, pelanggan, sopir armada harus melakukan login dengan cara mengisi username dan password. aksi aktor reaksi sistem melakukan daftar akun masuk melakukan pemesanan armada melihat informasi armada melihat riwayat pemesanan armada mengelola data armada mengelola data pelanggan mengelola data vendor mengelola data sopir mengelola data kota mengelola data pemesanan mengelola data laporan melihat jadwal pengiriman mengelola status pengiriman keluar pelanggan dapat melakukan daftar akun di dalam system user mengakses sistem pemesanan jasa ekspedisi pelanggan dapat melihat informasi armada pelanggan dapat melakukan pemesanan armada pelanggan dapat melihat riwayat pemesanan armada admin dapat melihat data armada admin dapat melihat data pelanggan admin dapat melihat data vendor admin dapat melihat data sopir admin dapat melihat data kota admin dapat memberi approval data pemesanan admin dapat mengelola laporan pemesanan jasa ekspedisi sopir dapat melihat jadwal pengiriman sopir dapat melihat status pengiriman user dapat keluar dari sistem kodisi akhir jika sesuai perintah maka aplikasi akan menampilkan menu yang dipilih oleh pengguna sumber: (lisnawanty & kurniawan, 2019) activity diagram gambar 2 activity diagram login user act activ ity diagram login masukan username masukan passw ord menentukan hak akses pengguna valid?tidak masuk kedalam sieksbar seasion login aktif masuk kedalam si-eksbar merge valid http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 40 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional rancangan basis data rancangan basis data pada sistem informasi ekpedisi barang pada pt. suksema abadi logistik digambarkan dalam bentuk entity relationship diagram (erd) berikut ini. gambar 5 entity relationship diagram (erd) sistem informasi ekspedisi barang c. desain user interface 1. akses login pengguna pada menu login adalah langkah awal membuka aplikasi, dengan batasan user akses ada didalamnya. gambar 6 akses login 2. halaman informasi armada pengiriman pada menu informasi armada, pelanggan dapat melihat ketersedian armada dan estimasi baiaya. sedangkan pada administrator dapat merubah informasinya berkaitan dengan tarif pengiriman. gambar 7 informasi armada pengiriman 3. halaman riwayat pemesanan armada pengiriman pada halaman ini dari sisi pelanggan bias melihat riwayat pengiriman dan dapat melakukan pesanan armada pengiriman kembali. gambar 8 riwayat pemesanan armada pengiriman 4. halaman penjadwalan pada halaman ini sopir dapat melihat jadwal pengiriman yang harus sopir kerjakan dengan data armada yang sudah tercantum didalam system. gambar 9 tampilan jadwal armada pada halaman sopir http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 2, no. 1 desember 2019 p-issn: 2656-1743 e-issn: 2656-1735 41 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional 5. halaman pengelola pada halaman ini yang bisa mengakses hanya level administrator, admin dapat mengeksekusi pesanan armada dan menjadwalkan sopir, menyetejui transaksi pembayaran diterima dari pelanggan. gambar 10 halaman pengelolaan pada halaman administrator 6. halaman pembuatan laporan pada halaman pembuatan laporan administrator dapat melakukan pencetakan laporan untuk yang di arsipkan dokumen fisiknya. gambar 11 menu pembuatan laporan d. pembuatan code program dalam pembuatan code program membutuhkan perangkat lunak (software) yang digunakan untuk pembuatan sistem informasi pada pt. suksema abadi logistik. sebagai contoh penerapan code aplikasi pada konfigurasi database ke system sis/config/database.php : '', 'hostname' => 'localhost', 'username' => 'root', 'password' => 'password', 'database' => 'sisfologistik', 'dbdriver' => 'mysqli', 'dbprefix' => '', 'pconnect' => false, 'db_debug' => (environment !== 'production'), 'cache_on' => false, 'cachedir' => '', 'char_set' => 'utf8', 'dbcollat' => 'utf8_general_ci', 'swap_pre' => '', 'encrypt' => false, 'compress' => false, 'stricton' => false, 'failover' => array(), 'save_queries' => true ); e. testing 1. pengujian laman aplikasi pada jenis aplikasi browser tabel 2. black box testing aplikasi pada browser 1. skenario pengujian buka dengan google chrome test case google chrome (terbuka) hasil yang diharapkan aplikasi dapat diakses dan tampilan sesuai dengan desain hasil pengujian sesuai harapan kesimpulan valid 2. skenario pengujian buka dengan mozila firefox test case mozila firefox (terbuka) hasil yang diharapkan aplikasi dapat diakses dan tampilan sesuai dengan desain hasil pengujian sesuai harapan kesimpulan valid 2. pengujian login aplikasi tabel 2. black box testing aplikasi pada halaman login 1. skenario pengujian jika salah satu kolom dikosongkan test case username: (kosong) hasil yang diharapkan aplikasi menolak akses dan menampilkan pesan “username atau password anda salah, silahkan coba lagi” hasil pengujian sesuai harapan kesimpulan valid 2 skenario pengujian kolom terisi namun tidak sesuai (username, password dan level akses tidak sesuai) test case username:(111111) password: (111111) hasil yang aplikasi menolak akses dan http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2, no. 1 desember 2019 42 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional diharapkan menampilkan pesan “username atau password anda salah, silahkan coba lagi hasil pengujian sesuai harapan kesimpulan valid 3 skenario pengujian kolom terisi dan sesuai (username dan password sesuai) test case username: (admin) password: (admin) hasil yang diharapkan aplikasi menerima akses dan mengantarkan pengguna ke halaman dashboard. hasil pengujian sesuai harapan kesimpulan valid f. support kebutuhan perangkat keras dan perangkat lunak dalam mengimplementasikan system informasi pada pt. suksema abadi logistik adalah sebagai berikut: 1. kebutuhan perangkat keras minimal. a. processor : 1.40 ghz b. memory : 8 gb c. harddisk : 500 gb d. monitor : resolusi minimun (1024 x 768) e. keyboard : 86 keys f. mouse : optical 2. kebutuhan perangkat lunak a. sistem operasi : linux server b. web server : apache c. database : mysql d. web browser : mozzila firefox /google chrome simpulan dan saran simpulan semakin besarnya integritas kebutuhan perusahaan maka perlu sebuah sistem yang bisa memenuhinya. sistem informasi pemesanan jasa ekspedisi ini dirancang untuk mengganti proses pemesanan jasa atau armada yang dilakukan secara manual menjadi sistem yang terkomputerisasi. melalui sistem pemesanan jasa ekspedisi berbasis web ini dapat memberikan solusi untuk memudahkan penggunanya dalam melakukan pemesanan jasa atau armada karena dapat dilakukan secara online yang dapat dilakukan dimanapun dan kapanpun, sehingga dapat meningkatkan efektifitas dan efesiensi dalam pengolahan data pemesanan jasa ekspedisi hingga pengolahan data laporan. meminimalisir adanya kesalahan human error yang terjadi. saran setiap perusahaan harus mampu memberikan fasilitas atau media yang dapat menunjang kinerja agar lebih optimal seperti membuat sistem pemesanan jasa ekspedisi barang kargo berbasis web atau online. untuk melindungi data dari kerusakan maka disarankan untuk backup data setiap hari. melakukan pemeliharaan sistem perangkat keras dan perangkat lunak secara berkala, agar dapat beroperasi dengan baik dan lancar. setiap karyawan di harapkan mampu untuk mempelajari setiap perkembangan teknologi, sehingga dapat memberikan kontribusi yang terbaik. daftar referensi fatayat, u., & frieyadie, f. (2019). penggunaan model waterfall dalam perancangan aplikasi penjualan kosmetik berbasis web. jurnal riset informatika, 1(4), 159–166. frieyadie, f. (2014). web sistem informasi berbasis w2000 untuk dukungan pemesanan dan penjualan produk safety. jurnal pilar nusa mandiri, 10(1), 111–116. hidayat, r. (2014). sistem informasi ekspedisi barang dengan metode e-crm untuk meningkatkan pelayanan pelanggan. jurnal sisfotek global, 4(2). kendall, k. e., & kendall, j. e. (2010). systems analysis and design. prentice hall press. lisnawanty, l., & kurniawan, b. (2019). sistem informasi akuntansi penerimaan dan pengeluaran kas berbasis web (studi kasus: pt. sinar kapuas cemerlang). jurnal riset informatika, 1(4), 187–196. palasara, n., sinnun, a., & tabrani, m. (2018). penerapan metode waterfall pada sistem informasi ujian online berbasis web. transistor elektro dan informatika, 3(2), 103–110. rabiatul, a. (2015). perancanaan strategis si/ti menggunakan four stage model pada dinas pendidikan kabupaten kubu raya kalimantan barat. jurnal khatulistiwa informatika, iii(2), 180–198. https://doi.org/10.1145/3132847.3132886 saifudin, s., & ardani, f. p. (2017). sistem informasi akuntansi penerimaan dan pengeluaran kas dalam meningkatkan pengendalian internal atas pendapatan pada rsup dr. kariadi semarang. jurnal rak (riset akuntansi keuangan), 2(1), 123–138. tabrani, m., kholil, i., & sinnun, a. (2019). implementasi rapid application development dalam membangun aplikasi koperasi simpan pinjam (studi kasus koperasi subur jaya mandiri kabupaten subang). sistemasi: jurnal sistem informasi, 8(1), 145–152. http://creativecommons.org/licenses/by-nc/4.0/ 37 development of manufacturing inventory management system using material requirement planning method ami rahmawati1*), rizal amegia saputra2, ita yulianti3 sistem informasi universitas nusa mandiri ami.amv@nusamandiri.ac.id1*) sistem informasi akuntansi kampus kota sukabumi universita bina sarana informatika rizal.rga@bsi.ac.id2, ita.iyi@bsi.ac.id3 (*) corresponding author abstrak inventori memiliki peranan penting dalam aktivitas bisnis. hal ini dikarenakan inventori berpengaruh terhadap perubahan pasar produksi serta mengantisipasi perubahan harga dalam permintaan barang yang banyak. pt. barkah jaya mandiri merupakan perusahaan yang bergerak dalam bidang manufaktur dimana pengelolaan inventory barang pada perusahaan tersebut masih dilakukan secara konvensional. hal tersebut menyebabkan timbulnya berbagai masalah seperti terjadinya selisih pada stok barang, ketidaksesuaian data dan laporan akhir serta kendala pada proses produksi apabila terjadi kekurangan maupun kelebihan bahan baku.oleh karena itu, melalui penelitian ini akan dibuatkan sistem berbasis desktop menggunakan bahasa pemrograman java dengan metode mrp (material requirement planning) agar dapat mengatasi permasalahan yang terjadi pada perusahaan tersebut. penggabungan antara model sdlc dan teknik pengumpulan data meliputi observasi, interview dan studi pustaka juga dilakukan pada penelitian ini guna tercapainya sistem yang akan dibangun agar sesuai dengan kebutuhan yang ditargetkan. dengan adanya sistem tersebut, pengelolaan data inventory pada perusahaan ini dapat dilakukan dengan mudah dan akurat serta mengefektifkan waktu dibandingkan dengan sistem berjalan sebelumnya, sehingga aktivitas pengadaan bahan baku manufaktur menjadi optimal dan kinerja karyawanpun menjadi lebih baik. kata kunci: inventori, pemrogramman java, material requirement planning, sdlc abstract inventory has an important role in business activities. this is because inventory has an effect on changes in the production market and anticipates price changes in the demand for many goods. pt. barkah jaya mandiri is a company engaged in manufacturing where the management of inventory at the company is still done conventionally. this causes various problems such as the occurrence of discrepancies in the stock of goods, discrepancies in data and final reports as well as obstacles in the production process in the event of a shortage or excess of raw materials. (material requirement planning) in order to overcome the problems that occur in the company. the combination of the sdlc model and data collection techniques including observation, interviews and literature study were also carried out in this study in order to achieve the system that will be built to suit the targeted needs. with this system, the management of inventory data at this company can be done easily and accurately and save time compared to the previous system, so that the procurement of manufacturing raw materials is optimal and employee performance is better. keywords: inventory, java programing, material requirement planning, sdlc introduction inventory can be interpreted as items stored for use or sale in the future or period (prasetya & prakoso, 2020). inventory has an important role in business activities (nur fazli & jumaryadi, 2019). this is because inventory affects changes in the production market and anticipates price changes in demand for large quantities of goods (mufida et al., 2019). inventory management information system is a system to collect and maintain data that mailto:rizal.rga@bsi.ac.id2 38 explains the inventory of goods and converts the data into information and report to users (indrian & sudarmadi, 2015). activities on inventory management in general consist of the data collection of overall inventory, expenditure, procurement and transfer of goods and so on (rahmadi & yusmiarti, 2016). the tighter business competition in the business world, speed and accuracy in acting is a major thing (pahlevi et al., 2018). strategies in data processing and supporting facilities are needed to help process data quickly and produce the necessary reports of the company (hasan, 2017). by utilizing the development of existing information technology, data processing is done easily and produce information that is needed accurately and effectively time, as well as costs incurred more efficiently (hengki & suprawiro, 2017). pt. barkah jaya mandiri is one of the companies in sukabumi regency engaged in manufacturing. inventory management of goods in this company is still done conventionally, especially on the recording of in and out of goods, demand for procurement of raw materials and reports of purchases and use in the quantity of items still using the receipt book. this causes various problems such as differences in the stock of goods, data discrepancies and final reports between warehouse heads and warehouse admins even when the data search takes a relatively long time (bustami, 2021). in addition, the planning of procurement of raw materials is still carried out based on estimates only, so it is not surprising if there is a shortage or excess of raw materials that can slow down the production process which leads to incorrect target delivery time to customers if there is a shortage of raw materials, and vice versa if excess will impact the high cost of storage and the risk of loss and damage to raw materials (pratama & latipah, 2019). based on these problems, it is proposed the creation of an application system for inventory management of goods as an alternative solution to the current problems. there are several similar studies that have previously implemented such systems as inventory information systems at riau university hospitals (nasution & frianti, 2019), cv. limoplast (nurlaela et al., 2019) and ud. berkah jaya (ariani & taufik, 2021). the three studies both utilize php programming language to build a webbased inventory information system in managing inventory or stock of goods so as to facilitate employees in making reports. but in this study, the system will be created desktop-based using java programming language to provide newness compared to previous research. on the other hand, the application of mrp (material requirement planning) method is also widely used in various research related to inventory because it is considered capable of controlling the amount of raw materials that must be prepared or purchased according to production needs (susmita & cahyana, 2018)(rishmaya, 2020). therefore, to provide novelty compared to previous research, the system will be built by implementing the mrp method into desktop-based programs using the java programming language to support the management of production processes, especially in controlling the supply of raw materials at pt. barkah jaya mandiri. the purpose of this research is to improve the weaknesses in the existing system by building a program that can cover the need to manage raw material inventory in pt. barkah jaya mandiri. with the system is expected to provide convenience and benefits for the company in optimizing procurement activities ranging from the management of raw material data, scheduling purchases, and making reports. research methods the data used as a means of supporting the achievement of this research was obtained by observation, interview and literature review. 1. observation this observation was carried out at pt. barkah jaya mandiri with the aim of being able to produce a better picture of the research that will be made. 2. interview this data collection technique is done by interacting and conducting questions and answers regarding the inventory management system to the warehouse admin at pt. barkah jaya mandiri. 3. literature review literature study was carried out by looking for various references including books and e-books related to making applications and supporting articles obtained from the internet. types of research this type of research is in the form of qualitative research. this research is a research that emphasizes on understanding the problems in social life based on the conditions of reality, a holistic, complex and detailed natural setting (anggito & setiawan, 2018). therefore, a case study approach was carried out to achieve the objectives of this study supported by the main data collection techniques including observation, interviews and literature study. 39 time and place of research this research was conducted in january 2021 at pt. barkah jaya mandiri which is located in the sukabumi industrial center complex (sentris) block d4 cipancur, cisaat kab. sukabumi west java province. research target / subject this study aims to update the system that is currently running at pt. barkah jaya mandiri by utilizing computer technology and building a desktop program in the inventory management system as a solution in dealing with problems that occur so as to improve and optimize employee performance. this was chosen for the reason that the development of computer technology today has very important and useful contributions in various fields of life, ranging from education, economics, geography, health, and others (prasanti & indirani, 2018). procedure the design of the program in this study was carried out using the waterfall model. this method is sometimes called a linear sequential model or classical life flow model which provides a sequential or sequential software lifeflow approach starting from requirements analysis, design, coding, testing and support stages (s. & shalahudin, 2018). data, instruments, and data collection techniques in addition to data collection techniques, sdlc model is also implemented as a method of software development in creating programs that will be built in this research. 1. need analysis this stage begins with an analysis of the specifications of the system requirements to be built such as goods data, incoming goods data, outgoing goods data and others, which will later be involved in making inventory management applications. 2. design design representation implemented in the form of erd and uml with the aim of describing the design of the system to be built so that the applications created can run optimally. 3. coding at this stage, the results of the design are translated into software programs with the java programming language in netbeans applications. in addition, the mrp method is also added in the program built in order to provide predictions of raw materials that must be prepared on the next production scheduling. material requirements planning (mrp) is a scheduling method for purchased plans and manufactured planned orders submitted for further analysis with regard to capacity availability (susmita & cahyana, 2018). the output generated from the mrp method is information that can be used to carry out production control in the form of orders arranged based on the timing of each component/item (pratama & latipah, 2019). 4. testing testing is done by testcomplete to know if the application used can run as needed. testcomplete is an automated testing tool used for functional testing and automated scripts can be composed from python, c++script, vbscript, jscript, or javascript languages as well. it supports different testing types and methods, for example; functional testing, unit testing, and gui testing (okezie et al., 2019). testcomplete has evaluated to test program in context to factors i.e. load performance, response time etc. with respect to the number of users or threads (lenka et al., 2018). 5. maintenance the maintenance phase can repeat the development process ranging from specification analysis to existing software changes, but not to creating new software. results and discussion system requirements analysis the stages of system requirements analysis in this study are described with the help of erd and uml. a. entity relationship diagram the following is a display of the erd designed for system development in this research: 40 figure 1. entity relationship diagram apa?? based on the erd, databases and tables that have been designed are then created using mysql. b. use case diagram there are two use case diagrams designed in this study, namely for warehouse admin and warehouse head. the following is a display of the warehouse admin use case: figure 2. warehouse admin use case diagram if the warehouse admin will manage goods data, division data, category data, supplier data, incoming goods data, outgoing goods data, procurement data, purchase report data, and goods usage report data, they must first log in. after logging in, the warehouse admin can enter the main menu. a warehouse head can only manage purchase report data and goods usage report data. to manage the data, the head of the warehouse is required to login first to the system. c. activity diagram the following is a figure of the activity diagram made in this study: figure 4. activity diagram 41 from the diagram (see figure 4.), it can be seen that the design of the proposed system is based on the system's previous procedures. d. class diagram in addition to use cases and activity diagrams, class diagrams were also made in this study which are presented in the following figure: figure 5. class diagram the diagram shows the design of the system structure/scheme that describes the classes, attributes, methods, and relations of each object. 1. implementation a. login page the initial view on the built system is a login page that can be seen in the following figure: figure 6. login page in this inventory program, if you log in as a warehouse admin, you can access all parts of the program that have been created such as item data, category data, division data, supplier data, incoming goods data, outgoing goods data, procurement of goods and reports. but, if you are logged in as the head of the warehouse, you cannot access all existing data, you can only access report data. b. main menu page furthermore, if the login is successful, the master menu will appear as shown in figure 7. figure 7. main menu page on the main menu page, various menus from the inventory application will appear that can be accessed by the warehouse admin and warehouse head. c. item data form page figure 8. shows a item data form page. in this form, warehouse admin can processing data including input, edit and delete inventory items contained in pt. barkah jaya mandiri. figure 8. item data form page 42 d. incoming goods data form page figure 9. shows a incoming goods data form page. this form can processing incoming goods data, such as the first item arrives, the item is inputted by the warehouse admin. figure 9. incoming goods data form page e. report page figure 10. shows a report page on the purchase of goods reported to the management. this report can be accessed on the system by warehouse admin and warehouse head. figure 10. report page f. planning form page the following is a display of the planning form page created using mrp method: figure 11. planning form page in this form, the mrp method is applied by dividing the time of product manufacture into 4 periods so that information can be obtained regarding the inventory of raw materials that are available and which must be purchased according to production needs. conclusions and suggestions conclusion by making an inventory management application in general, it can help simplify and optimize the performance of inventory management activities at pt. barkah jaya mandiri. the application of the mrp method in the system is also capable of producing information and scheduling the availability of raw materials needed in the production process. suggestion added security for applications made to avoid unwanted things such as human error. then make automatic data backups such as to the cloud to keep the data safe. references anggito, a., & setiawan, j. (2018). metodologi penelitian kualitatif (e. d. lestari (ed.)). cv. jejak. ariani, f., & taufik, a. (2021). sistem informasi inventory (sitory) berbasis web dengan metode framwork for the application system thinking (fast ). jatisi (jurnal teknik informatika dan sistem informasi), 8(2), 859–869. https://doi.org/10.35957/jatisi.v8i2.930 bustami, a. (2021). seputar perusahaan pt. barkah jaya mandiri. hasan, h. (2017). implementasi sistem informasi pengelolaan inventory fixed asset pada pt. ark logistics dan transport. jurnal perspektif, 15(2), 155–163. https://ejournal.bsi.ac.id/ejurnal/index.php/ perspektif/article/view/2044 hengki, h., & suprawiro, s. (2017). analisis dan perancangan sistem informasi inventory sparepart kapal berbasis web: studi kasus asia group pangkalpinang. jurnal sisfokom (sistem informasi dan komputer), 6(2), 121– 129. http://jurnal.atmaluhur.ac.id/index.php/sisf okom/article/view/258 indrian, k., & sudarmadi, s. (2015). sistem informasi inventory alat tulis kantor (atk) 43 menggunakan metode waterfall. jurnal techno nusa mandiri, 12(1), 69–76. http://ejournal.nusamandiri.ac.id/index.php /techno/article/view/499 lenka, r. k., mamgain, s., kumar, s., & barik, r. k. (2018). performance analysis of automated testing tools: jmeter and testcomplete. international conference on advances in computing, communication control and networking (icacccn). mufida, e., rahmawati, e., & hertiana, h. (2019). rancang bangun sistem informasi inventory pada salonkecantikan. jurnal mantik penusa, 3(3), 99–102. nasution, s., & frianti, r. a. (2019). sistem informasi inventori obat berbasis web di rumah sakit universitas riau. seminar nasional aptikom (semnastik) 2019, 0(0), 402–409. nur fazli, d., & jumaryadi, y. (2019). edisi 1 januari. ensiklopedia of journal, 1(2), 22–27. nurlaela, l., dharmalau, a., & parida, n. t. (2019). rancangan sistem informasi inventory barang berbasis web studi kasus pada cv. limoplast. journal of chemical information and modeling, 53(9), 1689–1699. okezie, f., odun-ayo, i., & bogle, s. (2019). a critical analysis of software testing tools. journal of physics: conference series, 1378(4). https://doi.org/10.1088/17426596/1378/4/042030 pahlevi, o., mulyani, a., & khoir, m. (2018). sistem informasi inventori barang menggunakan metode object oriented di pt. livaza teknologi indonesia jakarta. jurnal prosisko, 5(1). prasanti, d., & indirani, s. s. (2018). pengembangan teknologi informasi dan komunikasi dalam sistem e-health alodokter.com. jurnal sosioteknologi, 17. prasetya, e. b., & prakoso, b. (2020). perancangan sistem pengelolaan inventory dan pelayanan purna jual (sipenipal) berbasis web menggunakan metode fast (studi kasus : pt. anugrah global inti persada). tekinfo, 21(2), 32–39. pratama, n. a., & latipah. (2019). perancangan aplikasi perencanaan bahan baku menggunakan metode mrp ( material requirement planning ) pada pt. e-t-a indonesia. insand comtech, 4(2), 10–11. rahmadi, l., & yusmiarti, k. (2016). perancangan sistem informasi inventory di amik lembah dempo pagaralam. semnasteknomedia online, 4(1), 133–138. https://ojs.amikom.ac.id/index.php/semnast eknomedia/article/view/1246/0 rishmaya, r. (2020). sistem informasi pengendalian bahan baku menggunakan metode material requirement planning pada pd. samijaya sukabumi berbasis web. jurnal sistem komputer, 10(1), 17–23. https://doi.org/10.14710/jsk.v10i1.177 s., r. a., & shalahudin, m. (2018). rekayasa perangkat lunak terstruktur dan berorientasi objek (revisi). informatika bandung. susmita, a., & cahyana, b. j. (2018). pemilihan metode permintaan dan perencanaan kebutuhan bahan baku dengan metode mrp di pt. xyz. seminar nasional sains dan teknologi 2018 fakultas teknik universitas muhammadiyah jakarta, 10. 44 jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 35 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. sistem pendukung keputusan karyawan teladan pt. bank rakyat indonesia dengan metode simple additive weighting jodhy prayogo sistem informasi stmik nusa mandiri jakarta www.nusamandiri.ac.id jodhy.prayogo@gmail.com abstract in the decision making of exemplary employees, pt bank rakyat indonesia conducts in several ways, namely, taking an assessment of absenteeism per three months, and individual assignments given by the supervisor. data obtained after that must be processed back into an assessment to produce a model employee's decision. data is collected for collection of types of criteria such as attendance assessment, assessment of individual assignments from the results of the combined assessment data. data will be processed manually with a data processing application from microsoft excel. after processing it into the assessment data, the data will be checked again, the appropriate data will be given directly to the he ad of the department for the selection of quarterly exemplary employees. the existence of the simple additive weighting (saw) method can determine with many criteria in making an exemplary employee assessment decision and the time needed in data processing will also be faster and more efficient. the purpose of this study is to help companies in the process of selecting exemplary employees for the greatest value on attendance criteria is an alternative a4 or employee on behalf of nur hidayatullah, for the largest value on productivity criteria is alternative a27 selected employees are urfani meigasari, while for criteria on individual tasks values the biggest on alternative a26 or selected employees is denny septian, for the biggest value with the criteria of responsibility on the alternative a27 the selected employees are urfani meigasari and for the largest value of the supervisor assessment criteria on the alternative a27 the selected employees are urfani meigasari. keywords: decision support systems, exemplary employees, simple additive weighting abstrakdalam pengambilan keputusan karyawan teladan, pt bank rakyat indonesia melakukan dengan beberapa cara yaitu, mengambil penilaian dari absensi per tiga bulan, dan tugas individual yang diberikan oleh supervisor. data yang diperoleh setelah itu harus diolah kembali menjadi penilaian untuk menghasilkan keputusan karyawan teladan. data dikumpulkan untuk dilakukan pengumpulan dari jenis kriteriakriteria seperti penilaian absensi, penilaian tugas individual dari hasil data-data penilaian gabungan tersebut data akan diolah manual dengan aplikasi pengolah data dari microsoft excel. setelah diolah menjadi data penilaian lalu data tersebut akan di cek kembali, data yang sudah sesuai akan diberikan langsung ke kepala bagian untuk dilakukan pemilihan karyawan teladan pertriwulan. adanya metode simple additive weighting (saw) ini dapat menentukan dengan banyak kriteria dalam membuat suatu keputusan penilaian karyawan teladan serta waktu yang dibutuhkan dalam pemrosesan data juga akan lebih cepat dan efisien. tujuan penelitian ini untuk membantu perusahaan dalam proses pemilihan karyawan teladan untuk nilai terbesar pada kriteria absensi adalah alternatif a4 atau karyawan atas nama nur hidayatullah, untuk nilai terbesar pada kriteria produktifitas adalah alternatif a27 karyawan yang terpilih adalah urfani meigasari, sedangkan untuk kriteria pada tugas individual nilai terbesar pada alternatif a26 atau karyawan yang terpilih adalah denny septian, untuk nilai terbesar dengan kriteria tanggung jawab pada alternatif a27 karyawan yang terpilih adalah urfani meigasari dan untuk nilai terbesar dari kriteria penilaian supervisor pada alternatif a27 karyawan yang terpilih adalah urfani meigasari. kata kunci: sistem penunjang keputusan, karyawan teladan, simple additive weighting pendahuluan dalam pengambilan keputusan karyawan teladan, pt bank rakyat indonesia melakukan dengan beberapa cara yaitu, mengambil penilaian dari absensi per tiga bulan, dan tugas individual yang diberikan oleh supervisor. data yang diperoleh setelah itu harus diolah kembali menjadi penilaian untuk menghasilkan keputusan karyawan teladan. data dikumpulkan untuk dilakukan pengumpulan dari jenis kriteriakriteria seperti penilaian absensi, penilaian tugas http://creativecommons.org/licenses/by-nc/4.0/ issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 36 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. individual dari hasil data-data penilaian gabungan tersebut data akan diolah manual (oktaviani, merlina, & nurmalasari, 2018) dengan aplikasi pengolah data dari microsoft excel (frieyadie, 2016). setelah diolah menjadi data penilaian lalu data tersebut akan di cek kembali, data yang sudah sesuai akan diberikan langsung ke kepala bagian untuk dilakukan pemilihan karyawan teladan pertriwulan. penilaian ini dilakukan subjektif hanya oleh kepala bagian saja terkadang cara tersebut kurang efektif (erwandi, mulyani, & senjaya, 2018) karena data yang didapat harus diolah terlebih dahulu dengan aplikasi pengolah data seperti microsoft excel (frieyadie, 2016) yang dapat menyebabkan kesalahan dalam penginputan nilai yang akan diolah, dan dengan menggunakan proses manual (octavia & yanto, 2014), (ariato & siahaan, 2018) tersebut akan terasa lama (suheryana, sanjaya, & shobary, 2016) dan tidak efisien dalam menentukan karyawan teladan. dengan menggunakan proses manual (priahatin, 2016) tersebut akan terasa lama dan tidak efisien dalam menentukan karyawan teladan. kriteria – kriteria dalam menentukan karyawan teladan pt bank rakyat indonesia di divisi layanan dan contact center yaitu : kriteria absensi, produktifitas, penilaian dari supervisor, penilaian tugas individual untuk melakukan perubahan nilai atau permasalahan dari unit kerja, dan tanggung jawab. kriteria–kriteria tersebut memungkinkan didalam penilaian untuk menentukan peringkat setiap karyawan sesuai dengan kualitas karyawan itu sendiri. dan dengan menggunakan metode simple additive weighting perusahaan dapat melakukan penilaian untuk nilai-nilai karyawan teladan dengan akurat (murtina, 2015). tujuan penelitian ini untuk membantu perusahaan dalam proses pemilihan karyawan teladan. memberikan solusi dengan menerapkan metode simple additive weighting (saw) yang dapat menentukan banyak kriteria dalam membuat suatu keputusan penilaian karyawan teladan. memperbaiki pengolahan data penilaian dan menjadi pertimbangan agar lebih efisien. untuk media penentu dalam memilih dan menentukan karyawan yang berkualitas. bahan dan metode a. instrument penelitian instrument merupakan alat yang digunakan untuk melakukan sesuatu. sedangkan penelitian memiliki arti pemeriksaan, penyidikan, kegiatan pengumpulan, pengolahan , analisis dan penyajian data secara sistematis serta objektif. penelitian ini menggunakan instrument kuesioner yang ditujukan langsung kepada supervisor di divisi layanan pt bank rakyat indonesia untuk penentuan karyawan teladan. pada data kuesioner tersebut berupa kriteria – kriteria dalam penentuan karyawan teladan. setelah melakukan wawancara penulis mendapatkan 5 variabel dalam menentukan karyawan teladan, 5 variabel tersebut yaitu : tabel 1. tabel variabel penelitian kriteria nama kriteria c1 absensi c2 produktifitas c3 tugas individual c4 tanggung jawab c5 penilaian supervisor sumber: (prayogo, 2017) b. metode pengumpulan data dalam pengumpulan data penulis menggunakan metode sebagai berikut: 1. metode pengumpulan data dalam melakukan penelitian dibutuhkan data yang relevan, oleh karena itu penulis melakukan berbagai cara dalam mendapatkan informasi. dan dalam pembuatan skripsi ini metode pengumpulan data yang penulis gunakan adalah : a. data primer data primer adalah data yang langsung dikumpulkan oleh penulis dan data dikumpulkan langsung dari sumber pertama atau tempat objek penelitian dilakukan, data primer juga dapat diartikan sebagai data yang diperoleh dari sumber-sumber asli atau dari sumber pertama kali diperoleh. pengumpulan data primer dalam penelitian ini menggunakan metode obervasi dan wawancara. b. data sekunder dalam pengumpulan data sekunder ini yang menjadi sumber data sekunder adalah buku, jurnal, e-book, dan lain-lain. dan penulis mengumpulkan data sekunder yang didapat melalui study pustaka yang diperoleh dari literatur, jurnal, buku referensi yang berkenaan dengan penelitian yang dilakukan. 2. populasi populasi adalah wilayah generalisasi yang terdiri atas obyek atau subyek yang mempunyai kualitas dan karakteristik tertentu yang ditetapkan oleh peneliti untuk dipelajari kemudian ditarik kesimpulannya (sugiyono, 2015). populasi dalam penelitian ini adalah data pegawai pada divisi layanan dan contact center dalam menentukan karyawan teladan yang terdaftar di pt bank http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 37 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. rakyat indonesia dengan jumlah 35 karyawan periode tahun 2017. tujuan diadakannya populasi adalah agar dapat menentukan besarnya sampel yang diambil dari jumlah populasi. 3. sample penelitian sample pada penelitian ini berdasarkan dari tabel isaac dan michael dengan tingkat kesalahan ditetapkan sebesar 5% diperoleh jumlah sampel adalah sebesar 32 karyawan. sedangkan untuk teknik pengambilan sampel penulis menggunakan probability sampling yaitu memberikan peluang yang sama pada setiap populasi untuk di pilih menjadi anggota sampel. tabel 1. data karyawan pt bank rakyat indonesia divisi layanan periode tahun 2017 no nama pekerja supervisor jenis kelamin tanggal lahir personal number agama status pernikahan 1 wiata prima thasajati darwanto l 27/03/1985 90046821 islam menikah 2 erna widiastuti darwanto p 16/04/1987 90056517 islam menikah 3 muhamad lutfiansyah darwanto l 05/09/1989 90037429 islam belum menikah 4 nur hidayatullah darwanto l 27/11/1989 90085379 islam belum menikah 5 m fahmi rizki darwanto l 12/10/1989 90103467 islam belum menikah 6 anik puji lestari darwanto p 02/08/1992 90046890 islam belum menikah 7 deri arianto darwanto l 27/03/1990 90107652 islam menikah 8 lisa sulistyarini darwanto p 05/02/1991 90101857 islam belum menikah 9 hafizh qalam darwanto l 27/10/1993 90054200 islam belum menikah 10 muhamad budi pamuji irwan s. l 25/07/1991 90106542 islam belum menikah 11 nasfridona irwan s. l 20/04/1989 90122291 islam belum menikah 12 andi riyanto irwan s. l 08/03/1988 90100289 islam belum menikah 13 frengki tumpal irwan s. l 16/04/1983 90047842 kristen menikah 14 rahmat salim rumnie irwan s. l 11/07/1988 90092752 islam belum menikah 15 risky aditya salatin irwan s. l 23/07/1993 90046138 islam belum menikah 16 lesly wuisang irwan s. l 28/08/1989 90079196 kristen belum menikah 17 mohamad andika irwan s. l 17/02/1991 90071468 islam belum menikah 18 achmad faisal adhi c l 23/02/1987 90071458 islam belum menikah 19 mita erlina adhi c. p 02/12/1986 90104736 islam menikah 20 nahlah zafira lestari adhi c. p 24/05/1992 90104737 islam menikah 21 afriza adhi c. l 09/09/1988 90105472 islam menikah 22 irawan sapto aji adhi c. l 19/09/1988 90105665 islam belum menikah 23 zakaria adhi c. l 12/10/1986 90106021 islam menikah 24 denny septian adhi c. l 04/02/1987 90105781 islam belum menikah 25 melisa sitepu heri s. p 13/06/1989 90106809 kristen belum menikah 26 ade febi damanik heri s. l 27/03/1992 90109333 kristen belum menikah 27 urfani meigasari heri s. p 11/06/1990 90106812 islam menikah 28 herman heri s. l 03/08/1986 90050473 islam menikah 29 rahma wulandari heri s. p 24/08/1987 90102070 islam menikah 30 jodhy prayogo heri s. l 02/12/1991 90022201 islam belum menikah 31 putri safrita heri s. p 11/07/1993 90105568 islam belum menikah 32 rena isninna heri s. p 11/07/1994 90090935 islam belum menikah sumber: (prayogo, 2017) c. metode analisis data dalam mencapai tujuan penelitian maka analisis yang digunakan adalah data kualitatif dengan menggunakan metode simple additive weighting (saw), metode ini merupakan metode yang paling sederhana dan paling banyak digunakan dan juga metode yang paling mudah untuk di aplikasikan. hasil dan pembahasan menentukan karyawan teladan di pt bank rakyat indonesia, dengan jumlah data pada penelitian ini 36 karyawan. setiap karyawan disebut sebagai suatu alternatif (a1, a2, a3 dan seterusnya). a. pengolahan data dan perhitungan manual dengan metode saw http://creativecommons.org/licenses/by-nc/4.0/ issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 38 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. dalam proses ini tahapan yang diperlukan dalam pengolahan data adalah sebagai berikut : 1. analisa kebutuhan analisa kebutuhan dapat dibagi menjadi dua bagian, yaitu analisa kebutuhan input dan analisa kebutuhan output. untuk analisa kebutuhan input adalah variabel input yang digunakan untuk penelitian ini adalah: absensi, produktifitas, tugas individual, tanggung jawab, dan penilaian supervisor. sedangkan untuk analisa kebutuhan output pada penelitian ini adalah sebuah alternatif yang memiliki nilai tertinggi dibandingkan dengan alternatif nilai lain. 2. penyelesaian menggunakan metode saw pada tahap ini akan dilakukan pengujian terhadap hasil penelitian dengan menggunakan metode simple additive weighting (saw) yang digunakan dalam pengolahan data menentukan karyawan teladan pada pt bank rakyat indonesia. untuk melakukan perhitungan dalam menentukan karyawan teladan menggunakan metode simple additive weighting (saw) : a. langkah pertama menentukan alternatif, yaitu a1 berikut adalah data alternatif yang akan digunakan dalam perhitungan. tabel 2. data alternatif no alternatif kriteria absensi produktifitas tugas individual tanggung jawab penilaian supervisor 1 a1 3 2 2 3 4 2 a2 3 4 3 2 4 3 a3 2 2 4 4 2 4 a4 5 3 3 4 3 5 a5 3 4 4 3 4 6 a6 4 2 4 3 3 7 a7 3 3 2 2 4 8 a8 5 3 1 1 4 9 a9 3 4 2 2 4 10 a10 4 2 2 1 5 11 a11 2 3 2 3 4 12 a12 4 3 2 1 4 13 a13 3 4 5 2 5 14 a14 4 2 3 2 4 15 a15 3 2 4 2 5 16 a16 4 3 2 2 4 17 a17 3 3 4 2 4 18 a18 4 5 3 2 5 19 a19 5 2 3 3 4 20 a20 4 3 2 3 4 21 a21 4 4 3 2 4 22 a22 2 3 4 1 5 23 a23 2 3 3 2 5 24 a24 3 3 2 1 3 25 a25 3 2 4 2 3 26 a26 4 2 5 3 4 27 a27 4 5 3 4 2 28 a28 3 3 3 1 4 29 a29 2 3 2 3 4 30 a30 4 2 4 2 5 31 a31 3 2 3 1 5 32 a32 3 4 3 2 4 sumber: (prayogo, 2017) b. kriteria dan bobot dalam langkah kedua menentukan kriteria yang akan dijadikan acuan dalam pengambilan keputusan, yaitu c1. dan untuk dalam menentukan penilaian dibutuhkan kriteria, seperti absensi, produktifitas, tugas individual, tanggung jawab, dan penilaian supervisor. 1) absensi 2) produktifitas 3) tugas individual 4) tanggal jawab 5) penilaian supervisor kelima kriteria memiliki nilai dan pembobotan untuk variabel absensi ditunjukan pada tabel 3. tabel 3. absensi bilangan fuzzy nilai http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 39 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. kurang sekali (ks) 1 kurang (k) 2 cukup (c) 3 baik (b) 4 baik sekali (bs) 5 sumber: (prayogo, 2017) c. bobot preferensi (w) dalam proses penentuan ini bobot preferensi atau tingkat kepentingan untuk setiap kriteria. bobot kriteria yang digunakan untuk menentukan karyawan teladan pada pt. bank rakyat indonesia sebagai berikut : tabel 4. bobot kepentingan kriteria bobot (w) keterangan 0,2 kurang sekali 0,4 kurang 0,6 cukup 0,8 baik 1 baik sekali sumber: (prayogo, 2017) tabel 5. tingkat kepentingan (w) kriteria (c) bobot (w) keterangan c1=absensi 1 baik sekali c2=produktifitas 0,6 cukup c3=tugas individual 0,8 baik c4=tanggung jawab 1 baik sekali c5=penilaian supervisor 0,8 baik sumber: (prayogo, 2017) d. nilai rating kecocokan setiap alternatif pada setiap kriteria dalam menentukan rating kecocokan setiap alternatif pada setiap kriteria yang telah ditentukan pada tabel diatas ditunjukan pada tabel 5. tabel 5. rating kecocokan alternatif no alternatif kriteria absensi produktifitas tugas individual tanggung jawab penilaian supervisor c1 c2 c3 c4 c5 1 a1 3 2 2 3 4 2 a2 3 4 3 2 4 3 a3 2 2 4 4 2 4 a4 5 3 3 4 3 5 a5 3 4 4 3 4 6 a6 4 2 4 3 3 7 a7 3 3 2 2 4 8 a8 5 3 1 1 2 9 a9 3 4 2 2 4 10 a10 4 2 2 1 3 11 a11 2 3 2 3 4 12 a12 4 3 2 1 4 13 a13 3 4 5 2 5 14 a14 4 2 3 2 4 15 a15 3 2 4 2 5 16 a16 4 3 2 2 4 17 a17 3 3 4 2 4 18 a18 4 5 3 2 5 19 a19 5 2 3 3 4 20 a20 4 3 2 3 4 21 a21 4 4 3 2 4 22 a22 2 3 4 1 3 23 a23 2 3 3 2 4 24 a24 3 3 2 1 3 25 a25 3 2 4 2 3 26 a26 4 2 5 3 4 27 a27 4 5 3 4 5 28 a28 3 3 3 1 4 29 a29 2 3 2 3 4 30 a30 4 2 4 2 5 31 a31 3 2 3 1 3 http://creativecommons.org/licenses/by-nc/4.0/ issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 40 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. 32 a32 3 4 3 2 4 sumber: (prayogo, 2017) e. matriks keputusan setelah nilai pada rating alternatif setiap kriteria sudah ditentukan di langkah selanjutnya membuat matrix keputusan (x) yang dibentuk dari tabel rating kecocokan yang didapat dari semua kriteria. nilai (x) setiap alternatif (a1) pada setiap kriteria (c1) yang telah ditentukan. f. normalisasi keputusan (x) proses selanjutnya adalah proses normalisasi keputusan (x) ke skala yang dapat dibandingkan dengan semua rating alternatif yang telah didapatkan. rij = xij max xij …………………………………………… (1) nilai preferensi (v1) pada proses terakhir adalah menghitung hasil akhir preferensi (v1) yang diperoleh dari penjumlahan dan perkalian elemen baris matriks ternormalisasi (r) dengan bobot preferensi (w) yang bersesuaian dengan elemen kolom matriks (r). 𝑉𝑖 = ∑ 𝑊𝑗 𝑟𝑖𝑗 𝑛 𝑗=1 …………………………………….. (2) bobot preferensi : 1, 0.6,0.8,1,0.8 berikut hasil pengujian dimana nilai awal dari setiap alternatif diproses menggunakan metode simple additive weighting (saw) dan mendapatkan nilai hasil akhir dalam perhitungan seperti diatas, berikut tabel iv.10. tabel 6. hasil pengujian no alternatif kriteria hasil akhir absensi produktifitas tugas individual tanggung jawab penilaian supervisor c1 c2 c3 c4 c5 1 a1 0.6 0.4 0.4 0.75 0.8 2.55 2 a2 0.6 0.8 0.6 0.5 0.8 2.7 3 a3 0.4 0.4 0.8 1 0.5 2.68 4 a4 1 0.6 0.6 1 0.75 3.44 5 a5 0.6 0.8 0.8 0.75 0.8 3.11 6 a6 0.8 0.4 0.8 0.75 0.6 2.91 7 a7 0.6 0.6 0.4 0.5 0.8 2.42 8 a8 1 0.6 0.4 0.5 0.8 2.82 9 a9 0.6 0.8 0.4 0.5 0.8 2.54 10 a10 0.8 0.4 0.4 0.25 1 2.41 11 a11 0.4 0.6 0.4 0.75 0.8 2.47 12 a12 0.8 0.6 0.4 0.25 0.8 2.37 13 a13 0.6 0.8 1 0.5 1 3.18 14 a14 0.8 0.4 0.6 0.5 0.8 2.66 15 a15 0.6 0.4 0.8 0.5 1 2.66 16 a16 0.8 0.6 0.4 0.5 0.8 2.62 17 a17 0.6 0.6 0.8 0.5 0.8 2.74 18 a18 0.8 1 0.6 0.75 0.8 3.18 19 a19 1 0.4 0.6 0.75 0.8 3.11 20 a20 0.8 0.6 0.4 0.75 0.8 2.87 21 a21 0.8 0.8 0.6 0.5 0.8 2.9 22 a22 0.4 0.6 0.8 0.25 0.6 2.13 23 a23 0.4 0.6 0.6 0.5 0.8 2.38 24 a24 0.6 0.6 0.4 0.25 0.6 2.01 25 a25 0.6 0.4 0.8 0.5 0.8 2.46 26 a26 0.8 0.4 1 0.75 0.8 3.23 27 a27 0.8 1 0.6 1 1 3.68 28 a28 0.6 0.6 0.6 0.25 0.8 2.33 29 a29 0.4 0.6 0.4 0.75 0.8 2.47 30 a30 0.8 0.4 0.8 0.5 1 2.98 31 a31 0.6 0.4 0.6 0.25 0.6 2.05 32 a32 0.6 0.8 0.6 0.5 0.8 2.7 sumber: (prayogo, 2017) http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 1, no. 1 desember 2018 issn: 2656-1743 41 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. untuk nilai terbesar pada kriteria absensi adalah alternatif a4 atau karyawan atas nama nur hidayatullah, untuk nilai terbesar pada kriteria produktifitas adalah alternatif a27 karyawan yang terpilih adalah urfani meigasari, sedangkan untuk kriteria pada tugas individual nilai terbesar pada alternatif a26 atau karyawan yang terpilih adalah denny septian, untuk nilai terbesar dengan kriteria tanggung jawab pada alternatif a27 karyawan yang terpilih adalah urfani meigasari dan untuk nilai terbesar dari kriteria penilaian supervisor pada alternatif a27 karyawan yang terpilih adalah urfani meigasari. dari tabel 6, ini untuk nilai terbesar ada pada v27, sehingga untuk alternatif a27 atau karyawan yang terpilih menjadi karyawan teladan adalah urfani meigasari dengan penilaian 3,68. namun pada kasus ini alternatif yang terbaik adalah beberapa karyawan yang mendapatkan nilai pembobotan cukup pada setiap kriteria. kesimpulan berdasarkan uraian dan tinjauan dari pembahasan penelitian yang telah dilakukan, maka kesimpulan yang didapat dari penelitian yang telah dilakukan, proses penentuan karyawan terbaik pt bank rakyat indonesia dengan metode saw dimulai dengan pemberian nilai kriteria, pembobotan, rating kecocokan, normalisasi dan perangkingan. sehingga menghasilkan nilai untuk masing – masing kriteria. hasil dari perhitungan tersebut merupakan perangkingan nilai tertinggi ke nilai terendah, dan nilai tertinggi merupakan hasil yang dibutuhkan untuk menentukan karyawan terbaik. untuk nilai terbesar pada kriteria absensi adalah alternatif a4 atau karyawan atas nama nur hidayatullah, untuk nilai terbesar pada kriteria produktifitas adalah alternatif a27 karyawan yang terpilih adalah urfani meigasari, sedangkan untuk kriteria pada tugas individual nilai terbesar pada alternatif a26 atau karyawan yang terpilih adalah denny septian, untuk nilai terbesar dengan kriteria tanggung jawab pada alternatif a27 karyawan yang terpilih adalah urfani meigasari dan untuk nilai terbesar dari kriteria penilaian supervisor pada alternatif a27 karyawan yang terpilih adalah urfani meigasari metode simple additive weghting (saw) dapat memberikan alternatif keputusan yang terbaik dalam pengambilan keputusan. referensi ariato, e. y., & siahaan, f. b. (2018). analisa penilaian kinerja karyawan dengan metode fuzzy simple additive weighting pada pt. unilever indonesia tbk skin deo factory sbu production tube. jurnal teknik komputer, 4(1), 194–204. https://doi.org/10.31294/jtk.v4i1.2546 erwandi, d., mulyani, e. d. s., & senjaya, a. s. (2018). sistem pendukung keputusan untuk penilaian kinerja guru menggunakan metode weighted product (studi kasus : madrasah ibtidaiyah condong) | erwandi | konferensi nasional sistem informasi (knsi) 2018. in konferensi nasional sistem informasi (knsi) 2018 (pp. 870–876). pangkalpinang: stmik atma luhur. retrieved from http://jurnal.atmaluhur.ac.id/index.php/kns i2018/article/view/463 frieyadie, f. (2016). penerapan metode simple additive weight (saw) dalam sistem pendukung keputusan promosi kenaikan jabatan. jurnal pilar nusa mandiri, 12(1), 37– 45. murtina, h. (2015). sistem penunjang keputusan pemilihan supervisor menggunakan simple additive weighting pada pt nippon indosari corpindo. konferensi nasional ilmu pengetahuan dan teknologi, 1(1), 143–148. retrieved from http://konferensi.nusamandiri.ac.id/prosidi ng/index.php/knit/article/view/77 octavia, e., & yanto, a. h. (2014). penerapan metode fuzzy pada penilaian kinerja karyawan (studi kasus pt. indovisualjakarta). jurnal techno nusa mandiri, 11(2). retrieved from http://ejournal.nusamandiri.ac.id/ejurnal/in dex.php/techno/article/view/96 oktaviani, n., merlina, n., & nurmalasari, n. (2018). pemilihan jasa pengiriman terbaik menggunakan metode simple additive weighting (saw). jurnal sistem dan teknologi informasi (justin), 6(4), 219. https://doi.org/10.26418/justin.v6i4.29126 prayogo, j. (2017). laporan tugas akhir sistem pendukung keputusan karyawan teladan pt. bank rakyat indonesia dengan metode simple additive weighting. jakarta. priahatin, t. (2016). penerapan metode simple additive weighting (saw) untuk penentuan status pengangkatan karyawan. seminar nasional ilmu pengetahuan dan teknologi http://creativecommons.org/licenses/by-nc/4.0/ issn: 2656-1743 jurnal riset informatika vol. 1, no. 1 desember 2018 42 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional. komputer, 19–inf.24. retrieved from http://konferensi.nusamandiri.ac.id/prosidi ng/index.php/sniptek/article/view/9 sugiyono. (2015). metode penelitian kuantitatif kualitatif dan r&d. bandu: alfabeta. suheryana, m. d., sanjaya, r., & shobary, m. n. (2016). sistem penunjang keputusan penerimaan pegawai baru pada pt. ebdesk teknologi. seminar nasional ilmu pengetahuan dan teknologi komputer, 63– inf.68. retrieved from http://konferensi.nusamandiri.ac.id/prosidi ng/index.php/sniptek/article/view/17 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 5, no. 2 march 2023 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 219 the work is distributed under the creative commons attribution-noncommercial 4.0 international license mobile based student presence system using haar cascade and eigenface facial recognition methods suherman achmad1, nazori a z2, achmad solichin3 faculty of information technology universitas budi luhur jakarta, indonesia 1)1811600202@student.budiluhur.ac.id, 2)nazori@budiluhur.ac.id, 3)achmad.solichin@budiluhur.ac.id (*) corresponding author abstract using biometric technology for recording attendance in the school environment is still not widely done by researchers. in this study, a solution was proposed to the problems that occurred in the school environment where parents/guardians could not monitor the presence of their children in school. the solution offered is a student attendance recording system based on facial recognition algorithms (face recognition). the built system can record the presence of students when entering the classroom and when returning home or out of class. proposed methods for identifying student attendance are the haar cascade and eigenface algorithms. the system can also provide notice of attendance or absence of students in real time to parents/guardians via email that has been registered. based on the test results, the method can provide accurate and fast facial recognition results. the presence system developed based on mobile can recognize faces up to a distance of 200-300 cm with low and moderate light intensity. keywords: presence system, haar cascade classifier, eigenface abstrak pemanfaatan teknologi biometrik untuk pencatatan kehadiran di lingkungan sekolah masih belum banyak dilakukan oleh peneliti sebelumnya. dalam penelitian ini, diusulkan sebuah solusi atas permasalahan yang terjadi di lingkungan sekolah yang mana orang tua/wali tidak dapat melakukan monitoring terhadap kehadiran anaknya di sekolah. solusi yang ditawarkan berupa sistem pencatatan kehadiran siswa berbasis algoritma pengenalan wajah (face recognition). sistem yang dibangun dapat mencatat kehadiran siswa saat masuk ke kelas, maupun saat pulang atau keluar dari kelas. metode yang diusulkan untuk mengidentifikasi kehadiran siswa adalah algoritma haar cascade dan eigenface. sistem juga dapat memberikan pemberitahuan kehadiran maupun ketidakhadiran siswa secara realtime ke orang tua/wali melalui email yang telah terdaftar. berdasarkan hasil pengujian, metode tersebut mampu memberikan hasil pengenalan wajah yang akurat dan cepat. sistem presensi yang dikembangkan berbasis mobile mampu mengenali wajah hingga jarak 200-300 cm dengan intensitas cahaya rendah dan sedang. kata kunci: sistem presensi, haar cascade classifier, eigenface introduction the speed of access to information is currently the most fundamental need for managing and transferring data. the speed of access to information is currently the most fundamental need for managing and transferring data. existing and rapidly developing technology is now expected to build a system to provide solutions for disciplining students and providing benefits for schools. a series of evaluations conducted by administrative bureaus and administrative staff found several weaknesses related to the presence of learners. in this case, the system of recording attendance in schools is still manually done with a signature recording system, which is considered easy to manipulate, so the lack of information received by parents/guardians on the presence of their children in school. therefore, a computerized system can manage information quickly and accurately to help smooth activity and become one of the influential factors in improving the discipline of learners. facial recognition technology is growing and widely used for the identification process. facial recognition is one of the technologies that has now been applied to many applications in the field of presence (rijal & ariefianto, 2008; satwikayana et al., 2021; septyanto et al., 2020). among others, supporting the identification system in schools to become a tool to find out data collection such as names, nis, and majors, in addition to facial recognition conditions http://creativecommons.org/licenses/by-nc/4.0/ mailto:1811600202@student.budiluhur.ac.id1 mailto:achmad.solichin@budiluhur.ac.id3 p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 jurnal riset informatika vol. 5, no. 2 march 2023 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 220 the work is distributed under the creative commons attribution-noncommercial 4.0 international license that are input (input) system, is also a significant problem. related to this study, there are several similar previous studies. simaremare and kurniawan compare lbph and eigenface for recognizing three faces at once in a real-time situation (simaremare & kurniawan, 2016). the researchers tested the accuracy of both methods in recognizing three faces at once. the test was conducted on 300 samples of facial imagery with four lighting conditions, namely indoor and outdoor daylight. the results of this test showed that the accuracy rate of lbph is better than eigenface, with the average accuracy of lbph being 93.54% and eigenface being 63.54%. the false rejection rate (frr) in the lbph method is lower than that of the eigenface method, with the average frr lbph being 0.24% and frr eigenface being 6.38%. this study only compares the two methods and is not a merger of the two methods, so the results obtained are not maximal. another researcher compared eigenface and fisherface methods for face recognition (firasari et al., 2022). then, septyanto et al. proposed a facial recognition presence application using haar cascade algorithm (septyanto et al., 2020). this test was conducted on 13 starcross store employees, each conducting 30 presidency trials. successful absentees had success scores of 87%, and 13% failed from 390 attempts. some absenteeism that fails occurs because several factors can affect absenteeism, such as high lighting, jacked head position, and the use of attributes (hats, glasses, etc.). the result of this study is that the system can identify faces with a reasonable degree of accuracy, but has limitations in knowing the face if the lack of lighting, conversely if the lighting is high or too bright, then the face cannot be identified, for it requires additional methods to overcome such weaknesses. many studies have also used haar cascade (anarki et al., 2021; behera, 2020; sulistiyo et al., 2014). in another research, the fisherface method supports the academic system (amri & rahmata, 2016; firasari et al., 2022). the system is built using primary visual programming languages and databases using mysql. in this test, the results obtained differed from one face to another, and the results came out in the name of the class of study program majors. facial recognition processing in absenteeism can work well if the data in the database is not too much and at the same lighting, so the level of face search approaching in the database can be better. based on testing, the percentage of facial recognition success reaches 80%. the disadvantage of this panel is that the detection results are sometimes not maximal if the distance of the face with the webcam is far and the position is not by the webcam. another weakness is that the system cannot identify the face if the light is too bright or dark. mobile-based face recognition technology is a rapidly developing field with significant implications for security, law enforcement, and mobile applications (arisandi et al., 2018; samet & tanriverdi, 2017). researchers are currently investigating the accuracy and performance of mobile-based face recognition systems compared to traditional desktop-based systems (abuzar et al., 2020; alburaiki et al., 2021; rodavia et al., 2017). there is growing concern about the privacy implications of mobile-based face recognition and how it can be used to identify individuals without their consent or knowledge (ahmed khan et al., 2021). studies are being conducted to explore ways to improve the accuracy and performance of mobile-based face recognition systems. moreover, researchers are also studying the performance of mobile-based face recognition systems on diverse faces, including different races, ages, and genders. studies have found that some systems perform better than others on diverse faces and that there are significant disparities in performance depending on the demographic group. overall, ongoing studies in mobile-based face recognition focus on developing new algorithms and techniques to improve the technology's accuracy and performance, addressing privacy concerns, and improving performance on diverse faces. this android-based attendance identification system aims to comfort parents/guardians, improve student discipline, and connect information online. the formula of the problem in this study is how the process of identifying the presence of learners entering and exiting the classroom can be detected early, accurately, and on target. based on previous research mentioned above, it is necessary to build further research by combining two different methods to produce a model of the student presence system using android-based facial recognition patterns (samet & tanriverdi, 2017). research methodology this research method is used as a guideline for researchers to implement research so that the results achieved do not deviate from the goals set. in this case, the stages of research conducted are as follows: data collection stages http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 5, no. 2 march 2023 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 221 the work is distributed under the creative commons attribution-noncommercial 4.0 international license the data collection stages in this study are as follows: 1. literature studies or study review. this technique begins with collecting data by studying the necessary materials, concepts, and theories from several written sources (books, magazines, tutorials, etc.), and the necessary understanding will be used as a reference for the preparation of research. 2. direct observation. this technique will be held direct observation of the main symptoms of what is being studied. observations made in actual situations are necessary for particular purposes. 3. designing student presence identification applications to support the proposed student presence identification system to provide information to parents/guardians via email using android-based facial recognition. 4. prepare sample data as input in research. system development stages the stages of application system development of student presence using the waterfall model, where the model consists of analysis, design, programming (coding), testing, and maintenance. the stages of the process use the waterfall model as follows: 1. analysis at the analysis stage, collecting needs is complete, observed, defined in detail, and presented as a specification system. 2. design at this stage, the system design process is carried out by requirement on hardware and software to form the overall system architecture. software design will identify the basic abstraction of software systems and their relationships. 3. coding at the coding stage, software design is realized as a program. furthermore, the program that has been realized will be tested by verifying whether each unit meets its initial specifications. 4. testing at this stage, the program that has been tested is confirmed to have fulfilled the software. requirement. when fulfilled, the user can implement and use the software system. 5. maintenance this stage is the maintenance part of the system, which carries out the program's operation, such as changes or improvements of the user's needs due to adaptation to the actual situation. the waterfall model is seen in the image below. design and implementation 1. system planning starting from entering the classroom and then doing the presence automatically to enter as a student. an image of the activity diagram identification of the student's presence can be seen in figure 1. figure 1. activity diagram identifies student presence the flow activity diagram in figure 1 is described as follows: a. learners perform presence activities. if true, then the identification process of the presence is successful; if wrong, then facial matching is not successfully identified, and learners are asked to return to presence. b. after successful identification, the student's face will be read on the system. c. next, the system will store the student's face on the server. 2. design of functions and infrastructure the infrastructure on the system will be built based on mutually agreed needs; outside of unified modeling language (uml) design, there is also application design for the user interface. this system will be described as infrastructurally by students connected to the presence system server and parents/guardians as receiving information. to be more clear can be seen in figure 2 system network infrastructure. figure 2. design function and infrastructure http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 jurnal riset informatika vol. 5, no. 2 march 2023 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 222 the work is distributed under the creative commons attribution-noncommercial 4.0 international license the flow of the function and system infrastructure design in figure 2 is the stage in running the presence system. here is an explanation of the flow of system and infrastructure function design that can be done, including: a) the first step, learners make a presence using facial recognition through a webcam or smartphone camera b) step two, the system connected to the internet will verify the face of the learner and whether the face of the participant can perform facial matching on the system. c) in step three, the learner's facial data will be stored on the system storage media, where nis, name, class, and email parents/guardians are stored using facial recognition when making a facial list. d) step four, student data stored on storage media will automatically connect to the cloud or internet network. e) in the last step, parents will receive a message about their child's presence through an online email address. 3. system component each component in figure 2 has different functions. the function of each component will be explained as follows: a. the webcam component is hardware that serves as a tool to take the image of the face of learners. this webcam will be a facial matching tool when conducting presence checks and taking images of the learner's face. b. the interface component is software on a desktop computer that serves as a tool to design and create a system that can connect with the web to take images of students' faces. smartphone components are multi-function devices used to install android-based presence applications so that applications can be used easily and quickly. c. the facial image component performs facial recognition mechanisms with the help of a webcam or smartphone camera, and this face capture is helpful for storage in the database and as input at the time of the presence. d. internet components function as an intermediary between the user and the system. the design is simple to make it easier for users to access information. facial steps with haar algorithm the process of facial shortness is needed in several stages. in the haar method, the process of facial shortness looks as in figure 3. figure 3. facial shortness process from figure 3 above, it is determined in advance whether the area is detected whether there is an object or not. the next process is to detect objects using haar cascade classifier, with steps to be described as follows. a. calculate feature samples with the haar algorithm. figure 4. rectangular feature haar cascade figure 4 is the result of camera detection, where there is a blue box which is a frame with values y = 480 and x = 640. in the blue box is the exposed face. figure 5 is the result of facial detection that has been recorded, so it has a size of 240 x 320. an original image converted to grayscale is shown in figure 9 figure 5. face detection with haar-like feature figure 6. the difference in the original image with grayscale http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 5, no. 2 march 2023 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 223 the work is distributed under the creative commons attribution-noncommercial 4.0 international license from the results of figure 6, it will be converted into matrix values so that haar-like squares in the input image are obtained as follows in table 1. table 1. square haar-like image input 46 45 44 45 44 44 46 44 41 43 44 44 46 43 40 40 43 44 45 40 40 40 44 45 45 41 39 40 44 45 46 41 40 41 45 46 the process of calculating the dark value and the light value, i.e. feature value = number of pixel values (dark value) – number of pixel values (light value), thus generating the feature value haar = 213. to calculate the haar value feature using the summed area table, known as the integral image, first formed an integral value matrix image. here is the matrix of integral values obtained from the input image, as seen in table 2. table 2. the integral value of the image from the input image 46 91 135 180 224 268 92 181 266 354 442 530 138 270 395 523 654 786 183 355 520 688 863 1040 228 441 645 853 1072 1294 274 528 772 1021 1285 1553 the haar feature value of the matrix area above is calculated using the following formula: i(x',y')=s(a)+s(d)+s(b)-s(c). so that the haar value feature is obtained = (528+46-274-91) (772+91-528135) + (1021+135-772-180) = 213 the haar = 213 value feature is then compared to the threshold determined as object detection. if haar's feature value is higher than the threshold, it can be said that the area meets the haar filter. this process will continue to retest the area with other haar filters, and if all haar filters are met, then it is said that there are observed objects in that area. results and discussions facial matching steps with eigenface algorithm facial recognition algorithms begin by creating a matrix of columns from faces inputted into a database. a column matrix's average vector image (mean) is calculated by dividing it by the number of images stored in the database. in the eigenface algorithm, the first step before determining the eigenface value first arranges a flat vector image matrix. the process flow can be seen in figure 7. figure 7. facial recognition process facial recognition algorithms are performed through several stages. 1) the first step is arranging an s matrix set of all training images. here is a training image of two facial data, as seen in figure 8 and figure 9, each of which has a matrix value. 𝐶1 = [ 1 0 2 1 2 1 0 2 2 ] figure 8. training image image of face image 1 𝐶1 = [ 1 1 2 0 2 1 1 2 4 ] figure 9. training image image http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 jurnal riset informatika vol. 5, no. 2 march 2023 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 224 the work is distributed under the creative commons attribution-noncommercial 4.0 international license 2) the second step is arranging the entire training image into one matrix. [ 𝑎 𝑏 𝑐 𝑥 𝑦 𝑧 ] → [𝑎 𝑏 𝑐 𝑥 𝑦 𝑧] 𝐶1 = [ 1 0 2 0 2 1 0 2 2 ] → [1 0 2 0 2 1 0 2 2] 𝐶2 = [ 1 2 2 0 2 1 0 2 4 ] → [1 1 2 0 2 1 0 2 4] 3) here is a count of flat vector averages. sum up the entire row from the flat vector obtained so that a matrix measuring 1 x (h x w) will be obtained. 𝐶1 + 𝐶2 = [ 1 0 2 0 2 1 0 2 2 1 1 2 0 2 1 0 2 4 ] 𝐶1 + 𝐶2 = [2 1 4 0 4 2 0 4 6] next, divide the matrix result by the number of images n to get the flat vector average value. [ 2 1 4 0 4 2 0 4 6 2 ] = [1 1 2 0 2 1 0 2 3] 4) the following flat vector average value will be used to calculate the eigenface value of the facial image in the training image. using the flat vector average value above, the eigenface can be calculated. how to reduce the rows on the flat vector matrix with flat vector average values. if the result is below zero, the value is replaced with zero. 𝐶1 = 1 0 2 0 2 1 0 2 2 1 1 2 0 2 1 0 2 3 0 0 0 0 0 0 0 0 0 𝐶1 = 1 1 2 0 2 1 0 2 3 1 1 2 0 2 1 0 2 4 0 0 0 0 0 1 0 0 1 5) here is the identified process. the identification process calculates the eigenface value of the test face matrix to determine the eigenface and flat vector values. the results can be seen in figure 10.. 𝐶𝑡 = [ 2 2 4 1 2 2 2 4 4 ] figure 10. test image (testface) 𝐶𝑡 = [ 2 2 4 1 2 2 2 4 4 ] → [2 2 4 1 2 2 2 4 4] 𝐶𝑡 = [ 2 2 4 1 2 2 2 4 4 1 1 2 1 0 0 0 2 3 1 1 2 1 0 2 2 2 1 ] eigenface value of test image 𝐶𝑡 = [1 1 2 1 0 2 2 2 1] 6) once the eigenface value is obtained, it can be identified by determining the shortest distance with the eigenface of the eigenvector training image. here determines the smallest eigenface value of the two image faces that are already known eigenface values. the results can be calculated as follows. eigenface value c1 = (0 0 0 0 0 0 0 0 0 0 0) 𝐶1 = 0 0 0 0 0 0 0 0 0 1 1 2 1 0 2 2 2 1 −1 −1 −2 −1 0 −2 −2 −2 −1 c1 = 1+1+2+1+0+2+2+2+1 = 12 eigenface value c2 = (0 0 0 0 0 1 0 0 1) 𝐶1 = 0 0 0 0 0 1 0 0 1 1 1 2 1 0 2 2 2 1 −1 −1 −2 −1 0 −1 −2 −2 0 c2 = 1+1+2+1+0+1+2+2+0 = 10 the smallest eigenface value of the two image faces above obtained from the distance of the image of face one has the smallest value of 10. the identification results concluded that the test face was more similar to face two than face one. application testing once this pretension identification software using facial recognition is built, the next stage is the display trial stage. this trial stage includes testing from the beginning of student data entry to the face-matching process when doing the presence of entry and home. the details will be described as follows. 1. test the app's entry window the use of the application is initiated by the user who must log in first (figure 11), if the login is successful then the user can enter the system. there are menus that can be selected for activities in the http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 5, no. 2 march 2023 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 225 the work is distributed under the creative commons attribution-noncommercial 4.0 international license system according to the desired function (figure 12). figure 11. app login menu view figure 12. app main menu view 2. test the filling of data on the menu of the list of learners. before testing, you can perform the face detection display (figure 13). the detected face will show a blue focus box furthermore after the face is detected, data input on the face list (figure 14). if it has been saved, then if the face is detected, a green focus box will appear with a caption with the name according to the detected face. figure 16 shows the faces stored on list data. figure 13. face detection view figure 14. data input on the face list figure 15. faces of registered learners figure 16. faces stored on list data 3. test the filling of data on the class entry menu. on this menu, students will do the presence of entering the class by using their faces. the step is that the learner faces the application, which is approximately 30cm away, then the face will be detected in the blue box and then face matching, then the face and name of the learner and the duration of the face matching process will be seen on the green box, after which automatically the student data will be stored and sent to the parent/guardian email, like the figure 17, 18, and 19 below. http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 jurnal riset informatika vol. 5, no. 2 march 2023 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 226 the work is distributed under the creative commons attribution-noncommercial 4.0 international license figure 17. face entry detection figure 18. face entry match figure 19. the process saves incoming data and messages sent to the email 4. test data are filled on the out-of-class menu. in this menu, students will do the presence of exiting the class / going home using the face. the step is that the learner faces the application, which is approximately 30cm away, then the face will be detected in the blue box and then face matching, then the face and name of the learner and the duration of the face matching process will be seen on the green box, after which automatically the student data will be stored and sent to the parent/guardian email, like the figure 20, 21, and 22 below. figure 20. face entry detection figure 21. face entry matc figure 22 process save data home and messages sent to the email 2.1. system testing based on distance and intensity of light. this test intends to determine the objects detected or undetected that can present learners in the classroom by matching faces at different distances/radii and light intensity. here is a test by matching faces at a distance/ radius and intensity of light. figure 23. face matching distance 30cm figure 23 is a facial matching test from 0cm to 30cm with low light intensity. gambar 24. face matching distance 50cm figure 24 is a facial matching test from 0cm to 50cm with low light intensity. figure 25. face matching distance 100cm http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 5, no. 2 march 2023 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 227 the work is distributed under the creative commons attribution-noncommercial 4.0 international license figure 25 is a facial matching test at a distance of 0cm to 100cm with low light intensity. figure 26. face matching distance 150cm figure 26 is a facial matching test from 0cm to 150cm with low light intensity. figure 27. face matching distance 200cm figure 27 is a facial matching test from 0cm to 200cm with low light intensity. figure 28. face matching distance 250cm figure 28 is a facial matching test from 0cm to 250cm with low light intensity. figure 29. 300cm distance face matching figure 29 is a facial matching test from 0cm to 250cm with low light intensity. based on the facematching image that has gone through the application test process, the following summary of the results of the face-matching trial can be seen in table 3 below. table 3. presence test results with distance coverage and light intensity no detection object distance light intensity detecti on 1 figure iv30 0cm until 30cm low detected 2 figure iv31 0cm until 50cm low detected 3 figure iv32 0cm until 100cm low detected 4 figure iv33 0cm until 150cm low detected 5 figure iv34 0cm until 200cm low detected 6 figure iv35 0cm until 250cm low detected 7 figure iv36 0cm until 300cm low detected conclusion as for the conclusion of this study, where applications can be run automatically to read and analyze the presence of learners, applications can be run on android smartphones version 5.0 lollipop, 6.0 marshmallow, 7.0 nougat, 8.0 oreo, 9.0 pie, and android 10, in addition, this study can write the results of detection done either verbose when executed or written in true-false values entered in the processed database. this study has found the results of testing with the merger of two algorithms or methods that can recognize faces up to a distance of 300cm and obtain an average percentage of facial recognition system success reaches 90%, so that the application in this study can provide information to parents/guardians quickly, precisely and accurately. this research still has some limitations. therefore it still needs to be developed to increase effectiveness, efficiency, and the addition of features to support the right target presence. for that, it is necessary to develop subsequent systems, such as software and hardware, that must be met for this application to work correctly. this study is limited to locating learners and needs to be developed before it can be applied to other fields. references abuzar, m., ahmad, a. bin, & ahmad, a. a. bin. (2020). a survey on student attendance system using face recognition. icrito 2020 ieee 8th international conference on reliability, infocom technologies and optimization (trends and future directions), http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v5i2.340 jurnal riset informatika vol. 5, no. 2 march 2023 accredited rank 3 (sinta 3), excerpts from the decision of the minister of ristek-brin no. 200/m/kpt/2020 228 the work is distributed under the creative commons attribution-noncommercial 4.0 international license 1252–1257. https://doi.org/10.1109/icrito48877.2020. 9197815 ahmed khan, d., rizvi assistant professor, a., & scholar, d. (2021). ai based facial recognition technology and criminal justice: issues and challenges. turkish journal of computer and mathematics education (turcomat), 12(14), 3384–3392. https://www.turcomat.org/index.php/turkbi lmat/article/view/10923 alburaiki, m. s. m., johar, g. m., helmi, r. a. a., & alkawaz, m. h. (2021). mobile based attendance system: face recognition and location detection using machine learning. 2021 ieee 12th control and system graduate research colloquium, icsgrc 2021 proceedings, 177–182. https://doi.org/10.1109/icsgrc53186.2021. 9515221 amri, a., & rahmata, t. (2016). pengenalan wajah menggunakan metode fisherface untuk mendukung sistem akademik. proceeding seminar nasional ilmu komputer (seminasik), 1(1), 39–43. http://jurnal.umuslim.ac.id/index.php/semin asik/article/view/474 anarki, g. a., auliasari, k., & orisa, m. (2021). penerapan metode haar cascade pada aplikasi deteksi masker. jati (jurnal mahasiswa teknik informatika), 5(1), 179– 186. https://doi.org/10.36040/jati.v5i1.3214 arisandi, d., syahputra, m. f., putri, i. l., purnamawati, s., rahmat, r. f., & sari, p. p. (2018). a real time mobile-based face recognition with fisherface methods. journal of physics: conference series, 978(1), 012038. https://doi.org/10.1088/17426596/978/1/012038 behera, g. s. (2020, december 24). face detection with haar cascade. towards data science. https://towardsdatascience.com/facedetection-with-haar-cascade-727f68dafd08 firasari, e., cahyanti, f. l. d., sarasati, f., & widiastuti, w. (2022). comparison of eigenface and fisherface methods for face recognition. techno nusa mandiri, 19(2), 125– 130. https://doi.org/10.33480/techno.v19i2.34 70 rijal, y., & ariefianto, r. d. (2008). deteksi wajah berbasis segmentasi model warna menggunakan template matching pada objek bergerak. seminar nasional aplikasi teknologi informasi (snati), 1907–5022. https://journal.uii.ac.id/snati/article/view/8 91 rodavia, m. r. d., bernaldez, o., & ballita, m. (2017). web and mobile based facial recognition security system using eigenfaces algorithm. proceedings of 2016 ieee international conference on teaching, assessment and learning for engineering, tale 2016, 86–92. https://doi.org/10.1109/tale.2016.785177 6 samet, r., & tanriverdi, m. (2017). face recognitionbased mobile automatic classroom attendance management system. proceedings 2017 international conference on cyberworlds, cw 2017 in cooperation with: eurographics association international federation for information processing acm siggraph, 2017january, 253–256. https://doi.org/10.1109/cw.2017.34 satwikayana, s., wibowo, s. a., & vendyansyah, n. (2021). sistem presensi mahasiswa otomatis pada zoom meeting menggunakan face recognition dengan metode convulitional neural network berbasis web. jati (jurnal mahasiswa teknik informatika), 5(2), 785– 793. https://doi.org/10.36040/jati.v5i2.3762 septyanto, m. w., sofyan, h., jayadianti, h., simanjuntak, o. s., & dessyanto, b. p. (2020). aplikasi presensi pengenalan wajah dengan menggunakan algoritma haar cascade classifier. telematika : jurnal informatika dan teknologi informasi, 16(2), 87–96. https://doi.org/10.31315/telematika.v16 i2.3182 simaremare, h., & kurniawan, a. (2016). perbandingan akurasi pengenalan wajah menggunakan metode lbph dan eigenface dalam mengenali tiga wajah sekaligus secara real-time. sitekin: jurnal sains, teknologi dan industri, 14(1), 66–71. https://doi.org/10.24014/sitekin.v14i1.27 03 sulistiyo, w., suyanto, b., hestiningsih, i., mardiyono, m., & sukamto, s. (2014). rancang bangun prototipe aplikasi pengenalan wajah untuk sistem absensi alternatif dengan metode haar like feature dan eigenface. jtet (jurnal teknik elektro terapan), 3(2), 93–98. https://doi.org/10.32497/jtet.v3i2.180 http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 4, no. 1 december 2021 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v4i1.279 23 prediction of android handphone sales during pandemic using naïve bayes and k-nn methods based on particle swarm optimization endang sri palupi sistem informasi universitas bina sarana informatika endang.epl@bsi.ac.id abstrak pada masa pandemic sebagian besar sekolah, kampus, dan tempat pendidikan melakukan kegiatan belajar mengajar secara online. kegiatan belajar mengajar banyak dilakukan dengan menggunakan aplikasi zoom, google, webex, atau microsoft teams. semua itu bisa dilakukan melalui laptop, bisa juga menggunakan handphone (hp) sehingga kebutuhan akan laptop dan hp meningkat baik barang baru maupun barang yang bekas. walaupun dimasa pandemic keadaan ekonomi menurun, banyak perusahaan yang mengalami kerugian, sehingga terjadi pengurangan karyawan dan menimbulkan angka pengangguran yang tinggi, kebutuhan akan hp android tetap tinggi. selain untuk sarana pembelajaran jarak jauh secara online, hp android juga bisa digunakan untuk penjualan online melalui e-commerce, market place, media sosial, dan platform digital lainnya. saat ini hp android mempunyai banyak pilihan dan sesuai dana yang kita miliki, dengan berbagai brand dan spesifikasi. banyak merk mengeluarkan produk hp android dengan spesifikasi yang cukup bagus dan harga yang terjangkau, sehingga walaupun daya beli menurun akibat pandemi, penjualan hp android tetap banyak. dalam penelitian ini penulis memprediksi penjualan hp android yang terbanyak menggunakan metode naïve bayes dan metode k-nearest neighbor berbasis particle swarm optimization.hasil dari penelitian ini menggunakan algoritma naïve bayes yaitu sebesar 74.92%, sedangkan menggunakan algoritma k-nearest neighbor berbasis particle swarm optimization nilai akurasi sebesar 81.33%. kata kunci: android, k-nearest neighbor, naïve bayes abstract during the pandemic, most schools, campuses, and places of education conducted online teaching and learning activities. many teaching and learning activities are carried out using the zoom, google, webex, or microsoft teams applications. all of that can be done through a laptop, you can also use a cellphone (hp) so that the need for laptops and cellphones increases, both new and used goods. even though during the pandemic the economic situation was declining, many companies suffered losses, resulting in a reduction in employees and causing a high unemployment rate, the need for android phones remains high. in addition to online distance learning facilities, android phones can also be used for online sales through e-commerce, market places, social media, and other digital ceilings. currently, android phones have many choices and according to the funds we have, with various brands and specifications. many brands issue android cellphone products with pretty good specifications and affordable prices, so that even though purchasing power has decreased due to the pandemic, sales of android cellphones are still high. in this study, the author predicts the highest sales of android cellphones using the naïve bayes method and the k-nearest neighbor method based on particle swarm optimization. accuracy of 81.33%. keywords: android, k-nearest neighbor, naïve bayes introduction when the covid-19 pandemic hit indonesia, sales of android cellphones actually increased, both new and used cellphones. the need for an android cellphone is related to online teaching and learning activities from kindergarten to university level students, online business that many people do during a pandemic, for content creators and various activities can be done using an android cellphone during this pandemic. the author conducted a study to predict the most sales 24 of android cellphones during the covid19 pandemic to find out the biggest target market for indonesian people is the lower middle class. android cellphones at affordable prices but with good specifications and performance are the most widely purchased flagship by the public. various brands and types of android phones with competitive quality and prices are currently very busy on the market, so people have many choices depending on their needs and available funds. no matter how good the sophistication of a smartphone, it will be redundant and useless if it doesn't fit your needs. (solihin, 2017) prediction is an attempt to predict future conditions through testing past conditions. forecasting sales means determining the estimated amount of sales volume, even determining to make decisions or policies in accordance with the results of the sales predictions, before this scientific research is carried out the potential sales and market area controlled in the future. (wibowo, 2018). with this research, it is possible to predict sales of hp that are selling well and not selling well according to the interests of buyers, so that sellers can prepare inventory of goods in the future according to the interests of buyers and are expected to further increase sales and reduce the risk of loss due to stock items that are not selling well. in a previous study, eka pandu cyntia and edi ismanto in 2018 conducted a study entitled "c4.5 decision tree algorithm method in classifying sales data for fast food outlets" (cynthia & ismanto, 2018). the purpose of this study is to classify fast food outlets that are popular (selling) and less popular (less selling) using algortima c4.5. the results of this study indicate price amount sold food menu (rice bento = less selling, dada = selling) with the weight of each attribute: price (0.738), menu type (0.067), amount sold (0.156), status sales (0.040). in this study, eka pandu and colleagues only used one c4.5 algorithm and displayed only the decision tree, not calculating its accuracy. the results of this study are the value of each attribute used and what foods are selling well and not selling well. while in this study the authors predict sales of android phones using 2 methods of the decision tree algorithm and the k-nn algorithm as a comparison and calculate the accuracy of each algorithm. another study was written by juna eska in 2016 from stmik royal ksiaran entitled "application of data mining for wallpaper sales prediction using the c4.5 algorithm" (eska, 2016). the result of this research is that the highest factor influencing sales is the number of wallpaper motifs. the factors of price, size, quality of materials, and colors do not affect purchases because wallpapers with high prices, small sizes, good quality materials, and few colors are still in demand by customers. this study only uses the c4.5 algorithm method, previously calculated the gain and entropy values manually using excel, then for the decision tree using rapidminer, the results of the study are that the highest factor affecting wallpaper sales is motifs. while the writer uses the c4.5 algorithm, the k-nn algorithm as a comparison, the results of this study are the accuracy values of each algorithm and the conclusion is that the pso-based k-nn algorithm has a greater accuracy value than the c4.5 algorithm. the research entitled prediction of honda's best selling products with classification method using the c4.5 algorithm (case study: sales data of pt prospect motor, cikarang) was written by aswan s sunge and heri fidiawan in 2019.(sunge & fidiawan, 2019) from the research the accuracy obtained is 67.5%, while in this study the author uses 2 algorithms as comparison material, namely the c4.5 algorithm and the pso-based k-nn algorithm with greater accuracy using the psobased k-nn algorithm with an accuracy value of 81.33%. in 2020 alfian faiz i and sulastri conducted a research entitled "classification of android application sales using the c4.5 algorithm". this study classifies sales of applications that can be used on android. three classification experiments resulted in different accuracy values. the highest accuracy value is obtained from experiments with 210 training data and 90 testing data, which shows an accuracy rate of 73.3%. rating is the attribute that most influences the application that is classified as selling or not selling. the difference is that the research classifies sales of android applications, while in this study the authors predict sales of cellphones using android applications. this research only uses the c4.5 algorithm method, there is no comparison with other algorithms (alfian faiz izzulhaq1, 2020) in 2020 ahmad zakir and colleagues conducted a study entitled "application of data mining for classification of best selling food sales data with algorithm with c4.5 algorithm". the research was conducted at a burger shop, and implemented using the c4.5 algorithm with php programming language and mysql database. the result of this research is to produce a system that can determine which foods are selling well and not selling well using the c4.5 algorithm. the difference with this study is that the author uses two algorithms as a comparison with the results of the greatest accuracy value using the pso-based k-nn algorithm of 81.33%, and the author uses the jurnal riset informatika vol. 4, no. 1 december 2021 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v4i1.279 25 rapidminer framework in the implementation of the algorithm. (zakir, ndruru, & hadinata, 2020) in 2020 ismasari nawangsih conducted a study entitled "application of the naïve bayes algorithm to determine the classification of the best selling products in credit sales" in this study the authors performed calculations manually using the naïve bayes formula then calculated using rapid miner. the result of this research is that the name of the telkomsel pulsa product is the bestselling product and the accuracy value is 97.50% so that naïve bayes is a fairly good method in classification. while the authors in this study directly calculate using rapidminer to calculate accuracy using 2 algorithm methods, namely the naïve bayes algorithm and the pso-based k-nn algorithm, the results using the pso-based k-nn algorithm have a greater accuracy value of 81.33%. (ismasari nawangsih1) , 2020) this study aims to predict the most sales of android phones during the pandemic. in this pandemic period, the need for android cellphones is increasing, and with this research, it can be used as a reference for buying cellphones or buying and selling cellphones, what android cellphones are the most popular and currently selling the most. in addition, from the hp manufacturer's point of view, this research can also see what needs are most needed by the community in using hp in terms of features, price, specifications, and quality. predicting market needs is very difficult which is a problem faced by distribution companies. to find market needs, it is necessary to identify customer characteristics. (faradillah, 2013) research methods this research uses quantitative techniques. according to sugiyono, quantitative research methods can be interpreted as research methods based on the philosophy of positivism, used to examine certain populations or samples. (sugiyono, 2016). quantitative research can be defined as a process of finding knowledge by using data in the form of numbers as a tool to analyze information about what you want to know. this research method translates data into numbers to analyze the findings. the variables used in classifying bestselling products are types of goods, brands and prices with the target class being in demand and not selling well. these three variables are the benchmarks used in researching best-selling products in trading companies. (asmaul husnah nasrullah, 2021). types of research this type of research is quantitative, by taking data on sales of android cellphones during the period of the pandemic in indonesia. where during the pandemic the need for android cellphones actually increased for the teaching and learning process, business processes such as creating content or selling online through social media, marketplaces, and e-commerce. time and place of research this research was conducted in june 2020 when the pandemic occurred in indonesia, using hp sales data for the period june 2020 to may 2021 at itc cempaka mas, itc roxy mas, and several ecommerce sites in indonesia. research target / subject the target of this research is the productive age of android hp users from 12 years to 50 years. researchers conducted direct interviews, observations, and distributed google forms on whatsapp groups of students, junior high and high school students regarding the needs of hp and cellphones they currently have or want/have purchased. procedure this framework represents the steps and procedures that will be carried out in this research process. figure 1. cross-industry standard process for data mining (crisp-dm) 1. business understanding this study aims to predict the sales of android cellphones during the pandemic, which cellphones are the best and the least sold. it is hoped that with this research distributors can understand the needs of the community so that 26 in the future they can stock goods and sell goods according to the needs and desires of the community, thereby increasing sales and avoiding losses due to selling cellphones that are not selling well. 2. data understanding at this stage, the authors take hp sales data at hp stores in the itc cempaka mas and itc roxy areas. conduct observations and interviews with hp sellers and buyers. as well as making observations on e-commerce sales of android cellphones, what android cellphones sell best. sales data was taken when the pandemic occurred, which is between june 2020 to may 2021. 3. data preparation at this stage, all the data that has been collected there are some useless attributes that must be removed using delete useless attributes. the attributes used after this process are brand, type, price, ram, memory. 4. modeling the author does the modeling using rapid miner studio using the naïve bayes algorithm and the pso-based k-nn algorithm to get the accuracy value. the author uses 2 algorithms as a comparison to get the best accuracy value. 5. evaluation from the modeling results, it can be seen that using the pso-based k-nn algorithm modeling to get the best accuracy value compared to using the naïve bayes algorithm. 6. deployment the best results from this modeling use the pso-based k-nn algorithm with an accuracy value of 81.33%. data, instruments, and data collection techniques data collection using the following techniques: 1. interview interviews are used as a data collection technique to find problems that must be investigated and also if researchers want to know things from respondents more deeply. about behavior, and the meaning of that behavior (sugiyono, 2016). the author visited several hp shops at itc roxy mas and itc cempaka mas, to get data on any hp sales in the period june 2020 to may 2021. where in june 2020 and may 2021 there was an eid moment so that sales increased. the author also interviewed shoppers to find out what cellphones they wanted to buy or which had been purchased. 2. observation observation is a data collection method that uses direct or indirect observation (yatim riyanto, 2010). the author observes the sale of android cellphones in e-commerce such as shopee, tokopedia, jd.id, bhinneka.com, and others. by checking the number of items sold and the rating given by the buyer, as well as checking the best seller type of hp at that time in e-commerce. 3. questionnaire a questionnaire is a written list of questions given to the subject under study to collect the information needed by the researcher (kusumah, 2011). the author shares a google form link that contains questions related to the needs of hp and hp currently owned or that want / have been purchased on the student whatsapp group, high school and junior high school student whatsapp group. the result is that 110 people filled out the google form. data analysis technique put forward quantitative research, namely a research approach that uses a lot of numbers, starting from collecting data, interpreting the data obtained, and presenting the results. (arikunto, 2006). in this study, the author uses quantitative data analysis techniques, namely interviews with cellphone sellers and cellphone shop visitors, observing cellphone sales to various e-commerce, and distributing google form questionnaires to students, middle and high school students regarding the needs of cellphones that they already have or want to buy. a total of 110 people filled out the google form and the total data obtained was 500 datasets. with this research, the author wants to classify the types of android cellphones that are sold the most during the pandemic, where during the pandemic the community's economy is also experiencing a decline, but the need for android cellphones is also increasing with the online teaching and learning process, and activities that many people do during the pandemic. i.e. like content creators or selling online. results and discussion the following sales dataset used in this research is 500 data: table 1. sales data jurnal riset informatika vol. 4, no. 1 december 2021 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v4i1.279 27 data penjualan hp android juni 2020 mei 2021 n o merk type harga (idr) ram (gb) memor y bel i 1 xiaomi redmi 8a 1,400,000.00 4 256 no 2 samsun g galaxy a11 1,900,000.0 0 3 512 yes 3 samsun g galaxy a21s 2,900,000.0 0 3 128 no 4 xiaomi redmi note 8 pro 10,200,000. 00 4 256 yes 5 xiaomi redmi note 8 11,000,000. 00 4 256 yes 6 samsun g a51 4,700,000.00 3 256 no 7 xiaomi redmi 9a 1,100,000.0 0 3 256 no 8 samsun g galaxy m11 1,400,000.0 0 3 256 no 9 xiaomi poco x3 nfc 2,800,000.0 0 4 512 yes 10 realme c20 1,200,000.0 0 2 128 yes 11 infinix hot 10s 1,700,000.0 0 4 128 yes 12 samsun g galaxy a12 2,000,000.0 0 4 512 yes 13 tecno spark 7 pro 1,700,000.0 0 6 512 yes 14 xiaomi redmi note 10 2,300,000.0 0 4 128 yes 15 xiaomi poco m3 pro 5g 2,500,000.0 0 4 128 yes 16 infinix note 10 pro 2,500,000.0 0 8 128 yes 17 samsun g galaxy a325g 3,800,000.0 0 8 512 no 18 xiaomi poco x3 pro 3,500,000.0 0 8 256 yes 19 oppo a54 2,700,000.0 0 4 256 yes 20 oppo a15 2,500,000.0 0 4 256 yes 21 xiaomi redmi 9c 1,700,000.0 0 4 128 yes 22 samsun g galaxy a02 1,500,000.0 0 2 512 no 23 vivo y12s 1,800,000.0 0 4 256 yes naïve bayes classification figure 1. naïve bayes algorithm figure 1 is modeling using the naïve bayes algorithm using 500 datasets. figure 2. nave bayes algorithm validation process in figure 2 is the validation process using the naïve bayes algorithm modeling to get the accuracy value. figure 3. the results of the accuracy of the naïve bayes algorithm figure 3 shows the accuracy results using the naïve bayes algorithm of 74.92%, with true no 77.85% and true yes 74.18%. knn algorithm based on particle swarm optimization figure 4. design knn algorithm based on particle swarm optimization figure 4 is a design for weighting the knn algorithm based on particle swarm optimization using 500 datasets. figure 5. validation of the particle swarm optimization-based knn algorithm in figure 5 is the validation process of the psobased k-nn algorithm to increase the weight so that the accuracy value is better. figure 6. design knn algorithm based on particle swarm optimization 28 after the weighting process using pso, in figure 6 the modeling using the pso-based k-nn algorithm is ready to run to get a better accuracy value. figure 7. accuracy results of the particle swarm optimization-based knn algorithm the accuracy results in figure 7 using the psobased k-nn algorithm are better at 81.33% with true no 17.03% and true yes 99,12%. conclusions and suggestions conclusion the result of this study is the classification using the naïve bayes algorithm is an accuracy value of 74.92% with a true no recall class of 77.85% and true yes 74.18%. while the classification results using the particle swarm optimization-based knn algorithm have an accuracy of 81.33% with a true no 27.03% recall class and 99.12% true yes. classification using the particle swarm optimization-based knn algorithm has higher results than using the naïve bayes algorithm. dengan demikian algoritma k-nn berbasis pso bisa digunakan sebagai metode prediksi penjualan dengan hasil akurasi yang tinggi, sehingga dapat membantu meningkatkan penjualan. suggestion future research can use more varied data on questions about the applications needed, battery strength, camera needs and so on. correspondence segments interviewed can be from business people who use android cellphones, not just students and students. references alfian faiz izzulhaq1, s. (2020). klasifikasi penjualan aplikasi android. proceeding sendiu, (2019), 978–979. arikunto, s. (2006). suatu pendekatan praktik (revisi vi). jakarta: pt rineka cipta. asmaul husnah nasrullah. (2021). implementasi algoritma decision tree untuk klasifikasi produk laris. jurnal ilmiah ilmu komputer, 7(2), 45–51. cynthia, e. p., & ismanto, e. (2018). metode decision tree algoritma c.45 dalam mengklasifikasi data penjualan. jurnal riset sistem informasi dan teknik informatika (jurasi), (3) juli(july), 1–13. eska, j. (2016). penerapan data mining untuk prediksi penjualan wallpaper menggunakan algoritma c4.5. 2. https://doi.org/10.31227/osf.io/x6svc faradillah, s. (2013). implementasi data mining untuk pengenalan karakteristik transaksi customer dengan menggunakan algoritma c4. 5. pelita informatika budi darma, 5(3), 1– 5. kusumah, w. d. d. (2011). penelitian tindakan kelas. jakarta: pt indeks. solihin, s. r. (2017). 10 tips panduan memilih & membeli hp android berkualitas. retrieved from septian website: https://www.septian.web.id/10-tipspanduan-memilih-membeli-hp-androidbagus-berkualitas-html/ sugiyono. (2016). metode penelitian kuantitatif, kualitatif dan r&d. bandung: alfabeta. sunge, a., & fidiawan, h. (2019). prediksi produk laris mobil honda dengan metode klasifikasi menggunakan algoritma c4. 5 (studi kasus: data penjualan sales pt prospect motor, cikarang). jurnal sigma, 9(4), 97–103. retrieved from https://jurnal.pelitabangsa.ac.id/index.php/s igma/article/view/461 wibowo, d. a. (2018). prediksi penjualan obat herbal hp pro menggunakan algoritma neural network. technologia: jurnal ilmiah, 9(1), 33–41. https://doi.org/10.31602/tji.v9i1.1100 yatim riyanto. (2010). metodologi penelitian pendidikan. surabaya: sic. zakir, a., ndruru, y., & hadinata, e. (2020). penerapan data mining untuk klasifikasi data penjualan makanan terlaris dengan algoritma c45. jurnal ilmiah teknologi informasi dan robotika, 2(2), 7–12. retrieved from http://jifti.upnjatim.ac.id/index.php/jifti/arti cle/view/33 jurnal riset informatika vol. 3, no. 2 march 2021 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i2.188 137 the work is distributed under the creative commons attribution-noncommercial 4.0 international license the black box testing and loc method approach in testing and streamlining the patient registration program joosten information system stmik mikroskil https://www. mikroskil.ac.id joosten.ng@mikroskil.ac.id abstrak software yang baik dapat digunakan jika ada pengujian yang tepat. tahap pengujian cukup penting karena software perlu diuji sebelum digunakan oleh pengguna akhir. pada pembuatan software untuk rumah sakit hewan belum adanya validasi dan verifikasi sehingga diperlukan pengujian. penelitian ini menggunakan informasi bagian pendaftaran pasien rumah sakit hewan dan diuji dengan tiga metode black box testing, yaitu equivalence class partitioning (ecp), boundary value analysis (bva), dan decision table ditambah pendekatan loc. hasil pengujian dari ketiga metode tersebut adalah persentase ecp yang tidak valid lebih besar dari yang valid, sehingga perlu diubah lagi batas nilai inputnya. kemudian untuk pengujian bva, persentase yang valid lebih tinggi daripada tidak valid. dalam tabel keputusan dibuat aturan pemendekan antara layanan operasi dan layanan lainnya sehingga menghasilkan status rawat inap dan besaran uang muka secara otomatis tanpa harus memilih lagi dan diuji kembali oleh decision table dengan cara mencocokkan hasil estimasi dari kedua layanan tersebut. kata kunci: bva, decision table, ecp, pengujian, validasi, verifikasi abstract good software can be used if there is proper testing. the testing phase is quite important because the software needs to be tested before it is used by end users. in making software for animal hospitals there is no validation and verification so testing is needed. this study used information on the registration section of veterinary hospital patients and was tested by three black box testing methods, namely equivalence class partitioning (ecp), boundary value analysis (bva), and decision table plus the loc approach. the test results of the three methods are that the percentage of invalid ecps is greater than the valid ones, so the input value limit needs to be changed again. then for bva testing, the percentage of valid is higher than invalid. in the decision table, a shortening rule is made between operating services and other services so that it produces inpatient status and down payment automatically without choose it again and is tested again by the decision table by matching the estimation results of the two services. keywords: bva, decision table, ecp, testing, validation, verification introduction today technological developments are increasingly developing in this modern world. one of them is software development or what is called software. the widespread software applications of the internet and mobile computing have significantly increased the dependence on enabled software systems (xu et al., 2015). one of the stages in software development is software testing. the role of testing activities is very important because testing is one of the activities that must be carried out on software developed before the software is applied by users or end-users. there are three main reasons for the importance of software testing, namely errors or deficiencies in software can occur, the application must be the best, and end-user satisfaction is everything (solution, 2018). testing is the process of checking software, both internally and externally. from the internal side, testing is carried out to see the statements that have been tested. while on the outer side, testing is directed to find errors that arise from the software and ensure that the limited inputs can produce the desired actual results according to the expected results. the increasing demand for software makes the testing aspect always neglected. testing is an important part of the software development process (hierons & member, 2015). the complexity of the software programming logic flow that developers make is one of the problems when entering the testing phase. developers often find it difficult to get http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i2.188 jurnal riset informatika vol. 3, no. 2 march 2021 138 the work is distributed under the creative commons attribution-noncommercial 4.0 international license errors in the software they make due to algorithms that are too complex. users sometimes don't care if the software has an error or not. ignoring testing activities in the software results in the results (output) that is displayed sometimes not as expected. ordinary users will tell the developer to change the program they make in order to produce maximum results and satisfactory program performance. joel spolsky (spolsky, 2020), a software developer in new york city, wrote an article discussing the top 5 reasons (wrong) that a tester is not needed. joel is applying for a job at a company led by mr. gleick. joel asked mr. gleick about the pipeline that gleick created. joel sees that gleick's creation has problems such as not using an error correction protocol so that it can damage or crash. but gleick denies that pipeline has no bugs and is just as bad as ms. word from microsoft. both reasons from gleick kept joel from applying to gleick's company. from joel spolsky's case, it can be concluded that the average person ignores the validation, verification, and testing of the software that is made. neglect of software testing makes the software unable to work optimally and many errors occur. this study discusses several methods that can be used to test software so that the software can work optimally. the use of excessive costs in software testing causes the quality of the software to be poor. every year, poor software quality losses exceed $ 500 billion (shahbazi & miller, 2016). the national institute of standards of technology (nist) (rep, 2002) conducted a study in 2012 that explained the united states economy calculates a loss of $ 59.5 billion every year due to bugs in software created. nist explains about one-third of these losses can be avoided if the developers do software testing better. more than half the cost of fixing bugs given to software users is given to developers and vendors (wong et al., 2016). besides the use of large costs, another thing that assumes that software testing is not needed is the time spent. in the 1980s, one of the most notorious cases of software development failure was the ariane rocket (lynch, 2017). the rocket exploded due to software failure. as a result of the explosion of the rocket, the researchers over the years focusing their efforts on looking for problems or bugs in the software on the rocket. rashad khalid (khalid, 2017) conducted a study that focused on the efficiency side of software testing by combining two methods, namely the black box testing method with the white box testing method. khalid developed an automated analysis and testing technique consisting of two main steps: 1) the first step was to take the software under test (sut) and identify all files, input and output variables, and functions. 2) in the next step, the user selects the desired module part or function to test and selects the required tests such as dead-code, assertion based tests and exception tests. the programming language khalid tested was the c ++ programming language. khalid claims the tools he recommends can perform various tests such as static analysis, unit testing, dead-code testing, exception testing and assertion based testing. but the program code that khalid tested was only a simple program and did not tell from the efficiency side whether the recommended tool could handle the limited testing time or not so that the tool did not guarantee the success of the test when the program code was quite complex. christopher dimas satrio et al (satrio et al., 2018), conducted a study comparing a test case generation with two genetic algorithm approaches, namely mutual analysis and sampling. the two approaches will be compared from the reduction in test cases that occur. apart from reducing the test case, the number of iterations, the total number of individuals, the number of fitness evaluations, and the size of the test suites will also be a comparison between the two approaches. from the two approaches, it was found that the genetic algorithm mutual analysis approach was better than the genetic algorithm sampling in terms of the number of test case reductions and all the comparative variables applied. however, in terms of execution time, it is still assumed that the genetic algorithm mutual analysis is faster, so there has been no decision that the genetic algorithm mutual analysis approach is faster when executing larger sample data. researchers also concluded that to increase the effectiveness and efficiency in software testing by shortening the time that must be allocated for the testing carried out. but the researchers did not explain how long the time should be allocated, so they had to see how complex the software to be tested was. marcel bohme and soumya paul (bohme & paul, 2016), conducted a study that analyzed the efficiency between random testing (r) and systematic testing (s0). they built a general model for software testing by specifying a sampling strategy on random testing and systematic testing associated with cost and sampling time. they considered two such strategies whereby random testing was unaware of partition based errors and systematic testing that sampled each partition exactly once. they perform calculations on these two strategies to calculate the relative efficiency value. in the end they conducted 24000 simulation experiments with various parameters. however, in http://creativecommons.org/licenses/by-nc/4.0/ jurnal riset informatika vol. 3, no. 2 march 2021 p-issn: 2656-1743 |e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i2.188 139 the work is distributed under the creative commons attribution-noncommercial 4.0 international license this study there are recommendations from researchers to compare systematic testing techniques to random techniques with a given time limit practically because they assume random techniques must have the same "power" compared to systematic techniques so that there may be other testing techniques that can overcome the time required. limited compared to using random techniques. research methods this study uses methods to verify, validate, and test the hospital information system program. the methods used are equivalence partitioning (ep), boundary value analysis (bva), and decision table added with the line of code (loc) approach to count the number of rows before using the decision table and after using the decision table. these three methods are part of the black box testing method. black box testing is a software testing technique that focuses on the functional specifications of the software being developed (jaya, 2018). the way black box testing works is only to check the output value based on the software input value without knowing what program code is used. equivalence partitioning (ep) or what is often called equivalence class partitioning (ecp) is a technique or method that produces test data from several system requirements by grouping or dividing input data and testing the data in order to get several understandable and feasible categories (jahanbin & zamani, 2018). from these methods, there are several combinations that can occur in equivalence partitioning, including: a. valid and invalid input values b. a numeric value that is negative, positive, or zero c. an empty, non-empty string boundary value analysis (bva) (ardana, 2019) is a technique of the black box testing method that focuses on the input process by testing the values at the upper and lower limits. there are three principles that underlie the boundary value analysis (bva) method are: a. many errors occur with input errors b. select a test case that tests the limits of input values c. bva is a part of equivalence partitioning that selects elements in the equivalence class at the value limit. decision table is one of the techniques of the black box testing method that uses tables to perform testing and can also be used to shorten the logic flow of software programming. decision table testing (joosten et al., 2020) is a software testing technique used to test software on different input combinations by combining different input and output values and summarizing them into a table. decision table is also often referred to as a cause and effect table because of the several causes and effects used to create a decision table. the reason the decision table is quite important is as follows (joosten et al., 2020): 1. very helpful in test design techniques. 2. help testers to look for the effect of the combination of various inputs and the status of other software that must implement business rules properly. 3. provide a regular way to express complex business rules, which is beneficial for both developers and testers. 4. assist in the development process with a developer to do a better job. testing with all combinations might not be practical. 5. this method is basically a technique used in testing and managing requirements. 6. this method is a structured exercise to prepare the requirements when dealing with complex business rules. 7. it can also be used in complex logic models. line of code or what is often referred to as the source line of code (sloc) is a software metric that is often used to measure the size and complexity of a software project. there are two main types of sloc calculations, namely physical sloc (p-sloc) and logical sloc (l-sloc). the definition of p-sloc is the line count in the source code text of the program as well as comment lines and blank lines. meanwhile, l-sloc is responsible for measuring the number of expressions that can be executed. the intended expressions are operators, functions, etc. so if there is one or more statements which are followed by the end-of-line comment is a line of code and is counted into l-sloc. meanwhile, comment lines and blank lines will not be counted into l-sloc. in addition to physical sloc, logical sloc, comment line of code (cloc), blank line of code (bloc), there are also code & comment source line of code (c & sloc) and comment words (cword). to find out the calculation of the number of lines in a source code such as p-sloc, l-sloc, and others, below is an example of source code: #include #include #include using namespace std; int main () { char lagi; int name; int option; int number; int paid; http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 | e-issn: 2656-1735 doi: https://doi.org/10.34288/jri.v3i2.188 jurnal riset informatika vol. 3, no. 2 march 2021 140 the work is distributed under the creative commons attribution-noncommercial 4.0 international license int price; int total; int code; // create menu list // cout << endl ends list; early: system("cls"); cout<<"======================"<>code; from the sample source code above, the number of p-sloc is 29, the number of l-sloc is 24, the number of bloc is 1, the number of cloc is 2. in the source code above, there are c & sloc and cword. the part which is c & sloc is ‘cout< - home
http://creativecommons.org/licenses/by-nc/4.0/ p-issn: 2656-1743 e-issn: 2656-1735 jurnal riset informatika vol. 2 no. 1 desember 2019 6 ciptaan disebarluaskan di bawah lisensi creative commons atribusi-nonkomersial 4.0 internasional