Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2720 https://internationalpubls.com A Novel Learner Enrolment Predictive System Nivedita Sinha1, Vanshika1, Nikki Singh1, Kritika Kumari1, Sumanta Chatterjee2, Indranath Sarkar1 1Department of Electronics and Communication Engineering, 2Department of Computer Science and Engineering, JIS College of Engineering, Kalyani, India Article History: Received: 12-01-2025 Revised: 15-02-2025 Accepted: 01-03-2025 Abstract: Educational institutions are constantly seeking ways to optimize resource allocation, improve course scheduling, and ensure effective long-term planning. Anticipating learner enrolment trends is essential to achieve these goals. This paper introduces a comprehensive analysis of a Learner Enrolment Prediction System (LEPS) designed to accurately forecast future learner enrolment. LEPS utilizes a combination of historical enrolment data, demographic factors, socio-economic indicators, and academic performance metrics to identify patterns and project future enrolment trends. The system features a user-friendly interface, allowing administrators to input data, customize forecasting parameters, and visualize predictions through interactive dashboards and graphs. Furthermore, LEPS integrates a feedback mechanism to continuously update and refine its models, ensuring responsiveness to evolving educational trends. By providing data-driven insights into enrolment projections, LEPS enables institutions to make informed decisions regarding resource distribution, staffing, infrastructure expansion, and curriculum development. The implementation of LEPS has the potential to significantly enhance strategic management practices, leading to improved operational efficiency and overall institutional effectiveness. Keywords: Learner Enrolment, Forecasting, Analysis. 1. Introduction In the field of educational planning and administration, accurately forecasting Learner Enrolment trends is critical for institutions seeking to meet student needs and optimize their operations. Predicting future enrolment levels depends on multiple factors, such as demographic trends, economic conditions, institutional programs, and evolving student preferences. These complexities make enrolment forecasting a significant challenge for educational institutions, which must allocate resources, plan courses, and manage staffing levels effectively and so on. Traditional methods of forecasting, which often rely on simple extrapolation from historical data, may not fully capture the nuanced and evolving patterns that impact Learner Enrolment [1-4]. As educational landscapes become increasingly dynamic, the need for more sophisticated, data-driven approaches has grown. Recognizing this, there is a shift towards the adoption of advanced predictive modeling systems capable of utilizing comprehensive data sources, including historical records, demographic trends, and economic indicators, to produce more accurate and reliable enrolment forecasts. This paper proposes the development and implementation of a predictive modelling system for forecasting Learner Enrolment trends. By utilizing predictive analytics, such a system can produce accurate enrolment forecasts, allowing institutions to make well-informed decisions about resource allocation, budgeting, curriculum design, and staffing. Accurate enrolment forecasting plays a pivotal role in the strategic planning process, helping to improve operational efficiency and ultimately enhance Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2721 https://internationalpubls.com the quality of education provided to students and building their logic. This outlines the challenges faced by educational institutions in predicting enrolment trends, highlights the limitations of traditional forecasting methods, and emphasizes the importance of employing advanced, data-driven solutions for more effective. 2. Literature Survey In 2021 Chen, C. W. et.al. developed a model that explicitly connects the antecedents and outcomes of customer satisfaction within a utility-oriented framework [5]. This paper focuses on predictive modeling in higher education, exploring various approaches to developing Learner Enrolment forecasting systems. It thoroughly analyzes the integration of demographic data, academic performance metrics, and institutional factors into models aimed at accurately predicting future enrolment trends and data. The "Artemis" system at Florida Community College at Jacksonville (FCCJ) is a student-focused web portal. In 2002 Harr, Gary Lynn suggested through a proposal to expand its functions to integrate college resources, boost student retention, support distance learners, and improve operational efficiency through self-help tools [6-8]. Achieving these outcomes will require significant institutional commitment, resource reallocation, and potential reorganization, along with careful design and infrastructure considerations. In 2023 Cierva et. al. reported that the Bato Institute of Science and Technology's Online Enrolment System manages student details, grades, enrolment , and billing from admission to graduation [9]. With administrator and user access, the system ensures accuracy, ease of use, and reliability. A survey showed high satisfaction and effectiveness, with recommendations for ongoing improvements. In 2023 Mary Jane Pagay Cierva reported that The Bato Institute of Science and Technology Online Enrolment System efficiently manages student details, grade reports, enrolment , and billing, ensuring accurate record-keeping from admission to graduation. With computerized processing, the system enhances accuracy and simplifies backup maintenance. It operates with two access levels: administrator and user (staff and students). A user survey assessing ease of use, speed, and satisfaction confirmed the system's high efficiency, receiving a “very good” rating. Based on these findings, the system is deemed effective, with recommendations for continuous improvements to maintain its reliability in the future [10]. In 2022 R. Ramya et.al. provided insights to support the operational, managerial, and decision-making functions of enterprises and organizations. [11]. With the vast amount of information available, processing the student information management system is essential to enhance the efficiency of student management. This paper aims to develop a typical student information management system to achieve the systematization, standardization, and automation of student information management. This article examines the critical role of enrolment forecasting in enhancing educational planning. It outlines the methodologies employed in current enrolment prediction systems and emphasizes the impact of predictive analytic on optimizing resource distribution and institutional management. In 2021 Xiaomei Bai et. al. identified that the educational big data is a critical asset for advancing educational reform, encompassing student attributes, learning behavior, and psychological states [12- 15]. Its applications include predicting academic performance, employment recommendations, and financial support for low-income students. They have proposed that the predictive research in higher Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2722 https://internationalpubls.com education helps forecast student behavior and course outcomes. This report explores the significance of educational big data, academic performance prediction, and its key applications, while highlighting challenges and future research directions. Technology has become increasingly integral to academic instruction, especially during the pandemic. In 2018 was Purba Daru Kusuma has proposed that beyond enhancing teaching and learning delivery, technology's integration offers a long-term advantage in managing student data, crucial for preparing various standard school forms and records [16-18]. This study focused on developing the School Record and Forms-Online Management System (SRF-OMaS) to enhance enrolment and data management processes, specifically in generating school forms related to student registration, promotion, health records, academic progress, permanent records, and other essential reports [19]. In the year 2021 Anameje Chinwe A et al. reported a centralized database system where administration and college faculty and students can access data [20]. Educational institutions are increasingly focused on optimizing resource allocation, enhancing course scheduling, and ensuring effective long-term planning. A key component in achieving these objectives is the ability to accurately predict Learner Enrolment trends. Authors reported an in-depth analysis of a Learner Enrolment Prediction System (LEPS), developed to forecast future Learner Enrolment with high precision. LEPS leverages a combination of historical enrolment data, demographic trends, socio-economic factors, and academic performance metrics to build robust predictive models. These models utilize advanced techniques such as regression analysis, time series forecasting, and neural networks to identify patterns and predict future enrolment trends. This paper primarily focuses on developing a user-friendly interface for efficiently collecting and managing various student information. A student information system encompasses a wide range of data, from enrolment to graduation, including study programs, attendance records, and examination results. Ensuring seamless access to this data through an online interface is essential. The Student Information Management System offers a user-friendly interface for educational institutions to manage student records efficiently. Many universities and colleges had online platforms for enrolment and e-learning long before the pandemic, but they were underutilized, with a focus on in-person enrolment and face-to-face classes to foster student confidence. The pandemic, however, necessitated an immediate shift, as lockdowns forced people into their homes and halted normal activities. To comply with safety protocols, online processes became essential. Enhancing the Online Enrolment System is crucial to ensure students can continue their education without disruption. This system benefits parents, students, and institutions by simplifying the enrolment process for new, current, and returning students, offering a more convenient and accessible solution. This survey paper highlights future research directions and opportunities in Learner Enrolment prediction. It examines emerging technologies, including big data analytic and artificial intelligence, and explores their potential influence on the advancement and evolution of enrolment forecasting systems. In the year 2022 Niño V. Hayagan proposed that their is the need to keep the onlne platform benefits students, parents, and institutions by streamlining the enrolment process and making it more accessible for all students, including newcomers and returnees [21-22]. Inefficiencies in the advising and enrolment process each semester raised concerns among stakeholders, prompting the school to adopt a new system for organizing student records in a structured manner. This system was expected Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2723 https://internationalpubls.com to streamline and improve the advising and enrolment process. A queuing methodology was selected to develop a low-cost, affordable solution that integrated SMS and barcode technologies into a computerized enrolment system [23-24]. Previous studies have extensively focused on optimizing performance prediction systems to identify at-risk students and enhance the success of high-performing ones [25]. These studies span across various fields, including psychology, data mining, and data analysis, contributing to multiple performance prediction approaches for assessing student outcomes in cognitive tasks. However, there remains a lack of synchronization between these areas, leading to a continued reliance on real-world datasets and a delay in incorporating emotional factors into predictive models. This study analyzes 1,497 publications (1990-2022) to provide insights into key challenges and advancements in performance prediction. It evaluates the relationship between student performance and influencing factors, reviews current and modified prediction techniques, and highlights future directions to improve these systems. In the year 2019 Greg S. Campos proposed a new computerized system in replacement of the old school traditional paper based student record which was cost effective and improved the interaction between student and the administrator. Predictive models using historical data can assess students' learning behavior and identify those at risk of failing. These models help stakeholders detect learning difficulties and implement targeted interventions. This paper provides a systematic review of predictive analytic in higher education from 2008 to 2018, highlighting trends in data-driven models for gauging student performance. It also discusses machine learning techniques used in prior studies and explores strategies for future improvements [26-30]. 3. Proposed Methodology Fig.1. Activity Diagram of NLEPS Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2724 https://internationalpubls.com The given flowchart (Fig.1) represents the structure and navigation of a Novel Learner Enrolment Predictive System(NLEPS) . It visually outlines the key components of the system, how different user roles interact with the system, and the sequence of navigation from one section to another.The system starts with the Login Page, where users must authenticate themselves by entering valid credentials (username and password). The authentication process determines the role of the user (Admin, Student, or Staff) and grants access accordingly. A decision point labelled "Authenticated" directs users to their respective home pages based on their roles.If authentication is successful, the user is directed to one Admin Home Page, Student Home Page ,Staff Home Page .If authentication fails, the user remains on the login page until valid credentials are provided. The Admin Home Page provides an overview of the entire system and allows the administrator to manage various functionalities. From this page, the admin can navigate to course Management which allows the admin to add, delete, or update courses. Student Management that enables the admin to manage student records, including enrolment , performance tracking, and other administrative tasks. The Student Home Page provides students with access to essential information. Students can navigate to profile Details which displays personal information, including student ID, name, and other academic details. This also shows attendance Records: Allows students to view their attendance history and track their presence in classes. Leave Status Enables students to check the status of leave applications submitted to the administration. The Staff Home Page provides access to faculty-related information and records. Faculty members can navigate to attendance Records allows staff members to view and manage student attendance. Profile Details displays personal and professional details related to the staff members. This flowchart provides a structured representation of the NLEPS , ensuring smooth navigation based on user roles. The system optimizes administrative operations, enhances student experience, and facilitates seamless academic management. By dividing functionalities based on different user roles, the system ensures clarity, ease of access, and efficient resource management. 4. Output Fig.2 Shows the various sections of the Student Management System depicting Login Page, Admin Home Page, Student Home Page, Staff Home Page, Course Management (Admin View), Student Management(Admin View), Leave Status (Student View), Feedback Status (Student View). Login Page : The Login Page (Fig. 2) is the initial interface for users, requiring them to enter their user ID and password for authentication, ensuring secure access to personalized dashboards and institutional resources. Fig.2. Login Page Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2725 https://internationalpubls.com Admin Home Page : The Admin home Page (Fig. 3) provides an overview of total staff, students, courses, and subjects, enabling efficient management, quick access to records, and streamlined administration of institutional activities and resources. Fig.3. Admin Home Page Student Home Page : The Student Home Page (Fig. 4) provides access to profile details and attendance records, enabling students to track personal information, monitor attendance status, and stay updated on academic progress. Fig.4. Student Home Page Staff Home Page : The Staff Home Page (Fig. 5) displays personal profile details and attendance records, allowing faculty to track their work schedule, monitor leave balance, and stay updated on institutional responsibilities and notifications. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2726 https://internationalpubls.com Fig.5. Staff Home Page Course Management (Admin View): The Course Management page (Fig. 6) allows the admin to add or delete courses, update course details, and manage academic offerings efficiently to ensure a well- structured curriculum. Fig.6. Course Management (Admin View) Student Management(Admin View) : The Student Management page (Fig. 7) enables the admin to handle student records, update details, manage enrolment , and oversee academic progress, ensuring smooth administration and data accuracy. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2727 https://internationalpubls.com Fig.7. Student Management(Admin View) Leave Status (Student View) : The Leave Status page (Fig. 8) displays the current status of a student’s leave application, whether approved, rejected, or pending, helping them stay informed about their requests. Fig. 8. Leave Status (Student View) Feedback Status (Student View) : The Feedback Status page (Fig. 9) allows students to view responses to their submitted feedback, ensuring transparency and enabling communication between students and the administration for improvements. Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2728 https://internationalpubls.com Fig. 9. Feedback Status (Student View) 5. Conclusion In conclusion, the Learner Enrolment Prediction System, known as LEPS, represents a powerful tool for educational institutions seeking to optimize resource allocation, improve planning By utilizing historical enrolment data, demographic factors, and advanced predictive analytics, the Learner Enrolment Prediction System (LEPS) enables institutions to accurately forecast future enrolment trends. LEPS plays a crucial role in supporting data-driven decision-making, allowing educational leaders to anticipate changes in Learner Enrolment patterns and allocate resources efficiently. LEPS empowers institutions by streamlining administrative tasks such as registration and course planning, improving operational efficiency, and saving staff valuable time. With LEPS, educational institutions can reduce uncertainty and minimize guesswork, leading to more effective strategic planning and resource management. In today’s fast-paced, data-driven environment, a reliable enrolment prediction system like LEPS is essential for institutions to stay ahead of the curve. By embracing technology and leveraging data, educational institutions can make informed decisions and confidently adapt to shifting student demographics. In conclusion, LEPS is more than just a tool—it is a strategic asset that enhances an institution's ability to succeed in a competitive educational landscape. The future of enrolment management begins with LEPS. Refrences [1] Chen, C. W., Lin, C. J., & Lin, C. T. “A comparison of forecasting techniques for university enrolment .” (2021), Quality & Quantity, 40(2), 179-196. [2] Harr and Gary Lynn “Connections: A Comprehensive Student Portal. Concept Paper and Proposal” ERIC Number: ED474411 Publication Date: 2002-Dec [3] Cierva and Mary Jane P. “International Journal of Advanced Research in Computer Science,” 2023, Vol 14, Issue 5, p17, ISSN 0976-5697 Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2729 https://internationalpubls.com [4] Garcia, E., Garcia-Ruiz, M. A., & Cuadrado-García, M. (2020). Implementation of online enrolment systems in Latin American universities: A comparative analysis. Sustainability, 12(11), 4492. [5] R. Ramya and Mr. E. Ranjith “STUDENT INFORMATION MANAGEMENT SYSTEM,” International Journal of Research Publication and Reviews, Vol 3, Issue 6, pp 4550-4556, June 2022 [6] Xiaomei Bai, Fuli Zhang, Jinzhou Li, Teng Guo, Abdul Aziz, Aijing Jin, Feng Xia“ Educational Big Data: Predictions, Applications and Challenges” Volume 26 , 15 November 2021, 100270 [7] Purba Daru Kusuma, “Distance- Score Combined Model In Automatic High School-STUDENT ENROLMENT SYSTEM” Journal of Theoretical and Applied Information Technology, 31st October 2018. Vol.96. No 20 [8] Anameje Chinwe A; Okeke, Ogochukwu C. “Development and Implementation of Student Registration Portal (Case Study of Information Technology Department).” Volume. 6 Issue. 5, May - 2021, International Journal of Innovative Science and Research Technology (IJISRT), www.ijisrt.com. ISSN - 2456-2165, PP :- 218-223. [9] Niño V. Hayagan , "Paperless Enrolment System: Functionality and Credibility as an Online Platform", IJCSMC, Vol. 11, Issue. 7, July 2022, pg.110 – 118 [10] Greg S. Campos “Development of a Computerized Student- Advising and Enrolment System” Volume 1 Number 4, April 2019, Phillipines [11] Sadique Ahmad, Mohammed A. El-Affendi, M. Shahid Anwar and Rizwan Iqbal “Potential Future Directions in Optimization of Students’ Performance Prediction System” 17 May 2022 [12] Radhika Bhanushali1 et al Student Management System Volume 10 Issue VII July 2022 New Horizon Institute of Technology and Management Thane, India [13] Khajehzadeh, M., & Seifi, A. “Predicting student enrolment using genetic programming.” (2022), Journal of Computing in Higher Education, 26(2), 112-127 [14] Dr. K. VenkataSubbiah.et al. Int. Journal of Engineering Research and Application www.ijera.com, ISSN: 2248-9622, Vol. 6, Issue 8, ( Part -2) August 2016, pp.16-24 [15] YuvrajNaikM , A.Likhitha , D.TejaVardhan , D.Anusha , N.Fariza , S.Ganesh "Student Web Portal" International Journal of Research Publication and Reviews, Vol 3, no 6, pp 2375-2377, June 2022 [16] O. Bhaskar, K. Uday, K. Parimala, B. Haritha, N. Vijaya sai, K. Sai joshna , “E-LEARNING AND CAMPUS INFORMATION SYSTEM”, International Journal of Research Publication and Reviews, Vol 3, Issue 6, pp 2311-2313, June 2022 [17] Harr and Gary Lynn “Connections: A Comprehensive Student Portal. Concept Paper and Proposal” ERIC Number: ED474411 Publication Date: 2002-Dec [18] Jhanvi Agarwal, Renuka Singh, Mansi Singh, Mansi Raghav ,"DEPARTMENT MANAGEMENT SYSTEM [WEB-BASED APPLICATION" , International Journal of Engineering Applied Sciences and Technology, June2020 Vol. 5, Issue 2, ISSN No. 2455-2143, Pages 356-361 [19] Phani Kishore Rompicharla1, P Sumanth , Md Inamullah "COLLEGE ADMINISTRATIVE SYSTEM” , International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 07 Issue: 03 | Mar 2020 Marjan Mansourvar, Norizan Mohd Yasin “Web Communications on Applied Nonlinear Analysis ISSN: 1074-133X Vol 32 No. 9s (2025) 2730 https://internationalpubls.com portal As A Knowledge Management System In The Universities” , World Academy of Science, Engineering and Technology 70 2010 [20] Stephen McKenzie, Filia Garivaldis, Angelos Rodafinos "A FULLY ONLINE RESEARCH PORTAL FOR RESEARCH STUDENTS AND RESEARCHERS" , Journal Of Information Technology Education: Innovations in Practice ,Volume 17,2018 [21] Y. A. Baheshm1, A. O. Aldhaibani2, S. A. AL-Shami3, "Online Student Portal" , International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 02 | Feb 2021 Rupal More1, Neha Chavan2 , Nisarg Kendre3, Prof. Arti Devmane4 , "Rupal More1, Neha Chavan2, Nisarg Kendre3, Prof. Arti Devmane4 " , International Journal for Research in Applied Science & Engineering Technology (IJRASET) ISSN: 2321-9653; Volume 10 Issue IV Apr 2022 [22] Aryan Singh, Aakash Kumar, Rakshit Gola, Shivam Pandey, Saurabh Kaushik , "Student Portal Mobile Application" , International Journal of Research Publication and Reviews , Vol 5, no 5, pp 10044-10048 May 2024 [23] Azham Hussain; Sadiq Aliyu; Mustafa M. Barakat; Fatma Maki , "Issue Cover PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON APPLIED SCIENCE AND TECHNOLOGY (ICAST’18) 10–12 April 2018 Penang, "Assessing and testing the usability of student portal" , PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON APPLIED SCIENCE AND TECHNOLOGY (ICAST’18) , SEPTEMBER 26 2018 [24] Vamshi Krishna N 1, Sakthivel N ," Student Portal: An Online Platform for Students" , INTERNATIONAL JOURNAL OF PROGRESSIVE RESEARCH IN SCIENCE AND ENGINEERING, VOL.3, NO.03, MARCH 2022. [25] Adewole K.S. Mabayoje M.A. & Oke J.O,"Student Web Self-Service Portal for a Tertiary Institution,Covenant Journal of Informatics & Communication Technology Vol. 4 No. 2, Dec, 2016 [26] M Gupta and S arsden (2018), Lessons Learned from Implementing E-Learning for the Education of Health Professionals in Resource-Constrained Countries pp.12-30 [27] K Thuraya (2015), Improving the Effectiveness of E-Learning Implementation in the School of Engineering at Tripoli University. Doctoral thesis, University of Huddersfie [28] A. K. Prewar, T. D. Sofianti and d. Y. Indrayadi (2015), Developing E-Learning System to Support Teaching and Learning Activities Using DSDM Approach, Performa (2015) pp.41-52 [29] Mina Abdoli and Mahdi Javanmard ,"Supporting Learning Through The Use of Academic Portal" Advances in Natural and Applied Sciences, 8(10) Special 2014, Pages: 49-53 [30] Rupal More1, Neha Chavan, Nisarg Kendre, Prof. Arti Devmane , "Rupal More1, Neha Chavan2, Nisarg Kendre3, Prof. Arti Devmane4 " , International Journal for Research in Applied Science & Engineering Technology (IJRASET) ISSN: 2321-9653; Volume 10 Issue IV Apr 2022