Frontiers in Business, Economics and Management ISSN: 2766-824X | Vol. 15, No. 3, 2024 174 Data-driven Fixed Asset Management Innovation: Practical Exploration of Artificial Intelligence Applied to Data Analysis and Predictive Maintenance Yun Liu Sichuan Center for Disease Control and Prevention, China Abstract: This paper explores the transformative potential of integrating artificial intelligence (AI) into fixed asset management, with a particular focus on its practical application in data analytics and predictive maintenance. Effective internal controls in fixed asset management are paramount for organizations seeking to strengthen competitiveness, minimize risk, and optimize asset utilization. By leveraging AI-driven data analytics, organizations can delve deep into their asset portfolios to gain comprehensive insights that inform strategic decision-making and facilitate proactive maintenance protocols. Through a comprehensive literature review and methodological overview, this study highlights the various approaches and cutting-edge technologies used in fixed asset management, underscoring the critical importance of accurate valuation, efficient asset utilization, and regulatory compliance. In addition, real-world case studies and practical applications underscore the tangible benefits and transformative potential of AI-infused asset management practices, demonstrating their ability to revolutionize conventional methodologies and drive organizational performance to unprecedented levels. Keywords: Fixed Asset Management, Artificial Intelligence, Data Analysis, Predictive Maintenance, Innovation. 1. Introduction In order to enhance the competitiveness of enterprises, the internal control mechanism of fixed asset management has become particularly critical. This internal control system can not only ensure comprehensive and accurate management of fixed assets, but also effectively reduce potential risks and losses. By establishing a complete internal control mechanism, modern enterprises can better understand the status of their fixed assets, including quantity, value, usage, etc., thereby providing reliable data support for management decisions. An effective internal control mechanism for fixed asset management can help enterprises improve asset utilization and reduce resource waste and loss. By monitoring and evaluating the use of fixed assets in a timely and accurate manner, companies can better plan and optimize the allocation and utilization of assets to ensure that each asset can maximize its benefits. This not only helps to improve the production efficiency and operating efficiency of the enterprise, but also helps to reduce costs and increase profit levels. In addition, establishing a sound internal control mechanism for fixed asset management can also effectively reduce various risks faced by enterprises. Fixed assets are often one of the most important assets of a company. Improper management of fixed assets may lead to asset loss, damage or depreciation, thereby affecting the normal operation and development of the company. By establishing strict asset management policies and procedures and strengthening asset supervision and protection measures, enterprises can effectively reduce potential risks, respond to possible problems in a timely manner, and ensure the long-term and stable development of the enterprise. In addition to reducing risks and improving efficiency, establishing a complete internal control mechanism for fixed asset management can also provide important support for corporate strategic decisions. By accurately grasping the relevant information and data of fixed assets, enterprises can better formulate and adjust their development strategies, rationally plan asset investment and allocation, better respond to market competition and changes in the external environment, and enhance the competitiveness and risk resistance of enterprises. ability. Therefore, establishing a complete internal control mechanism for fixed asset management has become an inevitable choice for enterprises to enhance their competitiveness and achieve sustainable development. Enterprises need to strengthen their attention and investment in fixed asset management, continuously optimize internal control mechanisms, improve management level and efficiency, and lay a solid foundation for long-term development. In the Figure 1, the steps of the data-driven fixed asset management are illustrated. Figure 1. The Steps of the Data-driven Fixed Asset Management 175 In the forthcoming sections, we'll delve into the innovative domain of data-driven fixed asset management, with a particular focus on the practical application of artificial intelligence (AI) in data analysis and predictive maintenance. Introduction to Data-Driven Fixed Asset Management: We'll provide an overview of data-driven asset management, emphasizing its importance in modern business operations. Principles of AI in Asset Management: Explaining AI's foundational principles and how they enhance asset management practices. Data Analysis Techniques: Covering descriptive, diagnostic, predictive, and prescriptive analytics used to extract insights from asset data. Predictive Maintenance Strategies: Exploring how AI and data analytics enable predictive maintenance to anticipate equipment failures. Real-World Applications: Showcasing practical applications of AI-driven asset management through industry case studies. 2. Literature Review of Fixed Asset Management Managing fixed assets is critical to ensuring organizational stability and financial health. Several studies have examined various aspects of this process, including methodologies, technologies, and factors influencing optimization and decision making. This literature review summarizes findings from a selection of studies to provide insight into the current state of fixed asset management. Wicaksana et al. [1] delved into using Excel as a supplementary tool for village asset management systems. Their study aimed to enhance existing systems by providing more detailed information on fixed assets. Through quantitative analysis and evaluations by experts, they demonstrated the feasibility of using Excel-based applications to complement village asset management systems, thereby improving data accuracy and management efficiency. Konareva and Kruglyak [2] examined how fixed assets are managed within the context of enterprise resource planning (ERP) systems. Their study contributed to understanding how integrated systems facilitate effective tracking and decision- making regarding assets. By analyzing system functionalities, they provided insights into optimizing fixed asset management within an ERP framework. Golovetsky et al [3] examined methodological approaches to analyzing the financial aspects of fixed assets. Their study emphasized the importance of accurately valuing assets and identifying alternative strategies for renewal. By distinguishing between different types of asset costs, they aimed to improve financial analysis and decision-making processes. Saraubon et al. [4] proposed an innovative asset management system using Near Field Communication (NFC) and Internet of Things (IoT) technologies. By integrating these technologies, their system addressed the challenges associated with inaccurate asset tracking and recording. Their research demonstrated the feasibility of using advanced technologies to improve asset management processes and data accuracy. Gârleanu and Pedersen [5] presented a model that explores the relationship between market efficiency and asset management practices. Their research highlighted the impact of investor behavior and manager expertise on asset price efficiency, emphasizing the importance of informed decision making in asset allocation and management. Petchrompo et al. [6] addressed multi-objective portfolio asset management, proposing a method to refine optimal solutions for better decision-making. Their research aimed to optimize portfolio management by selecting representative solutions from complex sets of alternatives. Khoirudin et al. [7] conducted an analysis of optimizing fixed asset management in the Sleman Regency Government. Their study emphasized the role of asset inventory, valuation, and supervision in optimizing asset management processes, highlighting the importance of governance and regulatory compliance. McMahon et al [8] focused on the adoption of big data for railway asset management, highlighting the potential of data analytics technologies to improve decision- making processes. Their investigation highlighted the essential prerequisites and obstacles involved in implementing big data analytics for the railway infrastructure maintenance and optimization. Meanwhile, Boyes et al. [9] delved into the amalgamation of building information modeling (BIM) and geographic information systems (GIS) to enhance asset management in infrastructure projects. Their study tackled the hurdles of shifting from construction-centric to asset-centric information management and offered insights into refining asset management practices through spatial data integration. Furthermore, Wang et al. [10] proposed an enterprise asset management system leveraging IoT technology to address the shortcomings of conventional approaches. Their research showcased the viability of employing RFID technology for intelligent asset tracking and inventory management, thereby enhancing operational efficiency and precision. Moreover, Rifai et al. [11] scrutinized the financial and non-financial determinants influencing fixed asset revaluation in banking institutions. Their findings underscored the importance of fixed asset intensity and company size in shaping revaluation decisions, providing valuable guidance for financial analysts and decision-makers in the banking sector. The reviewed literature provides valuable insights into managing fixed assets, covering various aspects such as methodologies, technologies, and influencing factors. By synthesizing findings from diverse studies, this review contributes to advancing knowledge and informing best practices in fixed asset management across different sectors. 3. Methodology 3.1. The Artificial Intelligence Applied to Data Analysis Artificial Intelligence (AI) [12]-[14] applied to data analytics represents the revolutionary approach to extracting valuable insights from large data sets. By seamlessly integrating AI techniques with data analysis processes, organizations can dramatically improve the efficiency, accuracy, and depth of their analysis, transforming decision making across multiple industries. 176 Table 1. The Artificial Intelligence Applied to Data Analysis Methods Details Advanced Learning Algorithms AI-driven data analysis harnesses sophisticated learning algorithms to discern patterns, trends, and correlations within datasets autonomously. These algorithms, spanning from decision trees to neural networks, empower predictive modeling and classification tasks with unparalleled accuracy and precision. Language Understanding Technology Utilizing language understanding techniques, AI systems can parse and understand unstructured textual data, such as customer feedback, social media posts, and documents. This capability enables organizations to extract valuable insights regarding customer sentiments, market dynamics, and competitive landscapes from text data. Anomaly Detection AI-driven anomaly detection algorithms play a pivotal role in identifying irregular patterns or outliers within datasets, signaling potential anomalies or abnormalities warranting further investigation. This capability proves invaluable across domains such as fraud detection, network security, and predictive maintenance applications. Personalized Recommendation Systems By harnessing the power of AI, recommendation systems delve deep into understanding user behavior and preferences to craft personalized recommendations, thereby elevating user engagement and satisfaction to new heights. These systems find widespread application across diverse domains such as e-commerce platforms, streaming services, and content websites, where they play a pivotal role in delivering tailored suggestions spanning a spectrum of offerings including products, movies, and articles, all finely curated to align with individual user interests and preferences. Similarly, within the realm of streaming services, recommendation systems leverage AI algorithms to analyze viewing history, genre preferences, and user ratings to offer a curated selection of movies, TV shows, and music tailored to each user's preferences. Whether it's discovering new releases, binge-worthy series, or hidden gems within a preferred genre, these recommendations cater to individual tastes, fostering a deeper connection with the platform and promoting prolonged engagement. Continuous Learning and Adaptation AI-powered data analysis systems exhibit the capacity for continuous learning and adaptation to evolving data patterns and trends. Through feedback mechanisms and adaptive algorithms, these systems iteratively enhance their performance and accuracy, ensuring analysis results remain relevant and up-to-date. 3.2. The Fixed Asset Management In the considered scheme, the fixed assets of administrative institutions are selected. State-owned property is distributed in two main areas: state-owned enterprises and administrative institutions. In administrative institutions, fixed assets constitute a crucial component of state-owned property, supporting their operations and service provision. These fixed assets typically have been in use for more than one year (excluding the first year), possess a certain value, and generally retain their original form during use. Broadly speaking, fixed assets in administrative institutions can be categorized into six groups: buildings, specialized equipment, general equipment, cultural artifacts and exhibits, books and archives, and furniture, animals, and plants. In contrast to enterprises, administrative institutions primarily depend on state financing, which is characterized by its public and non- commercial nature. Enterprises are oriented towards profit maximization, whereas administrative institutions are dedicated to providing the social services. Consequently, while administrative institutions prioritize capital management, they often overlook the management of fixed assets, leading to sub-optimal utilization efficiency and negative consequences. Thus, administrative institutions should enhance the management and maintenance of fixed assets, optimize their utilization efficiency, and enhance their capacity to serve society. According to the relevant regulations and methods for the management of fixed assets of administrative institutions in my country, the management of fixed assets of administrative institutions covers basic management of fixed assets owned or used by the unit, standardizing management behaviors, improving management systems, and strengthening supervision and inspection. These measures aim to ensure the rational use and effective management of fixed assets to safeguard the safety and integrity of state-owned assets. In daily management, administrative institutions should establish a sound fixed asset ledger and file management system, conduct regular asset inventory and assessment, and timely update fixed asset information to ensure the accuracy and completeness of asset information. In addition, administrative institutions should also strengthen the maintenance and technological updating of fixed assets, improve the efficiency and service life of assets, and maximize the value and benefits of assets. The goals of fixed asset management mainly include the following three aspects: First, coordinate and strengthen fixed asset management to ensure the safety and integrity of state-owned assets. As an important part of national institutions, the safety and integrity of fixed assets of administrative institutions are directly related to national interests and social stability. Therefore, strengthening the management and supervision of fixed assets and ensuring that assets are not lost or misappropriated is the primary goal of fixed asset management in administrative institutions. Improving the efficiency of asset use, rationally allocate and effectively utilize fixed assets to ensure and promote the efficient performance of the functions of administrative institutions. The effective use of fixed assets can not only improve the work efficiency and service quality of administrative institutions, but also reduce capital costs and operating risks and maximize the use of resources. Therefore, administrative institutions should strengthen the rational allocation and use management of fixed assets and give full play to the benefits and value of assets. For further, improving the efficiency of asset use and reduce the financial pressure on the governments at all levels. As one of the main expenditure departments of the national finance, the management and use of fixed assets of administrative institutions are directly related to the government's fiscal balance and economic development stability. Therefore, by improving the efficiency of fixed assets, optimizing resource allocation, and reducing operating costs, we can effectively reduce the pressure on government finances and make positive contributions to national economic development. 3.3. The Fixed Assets Forecasting and Managing Suggestions The combination of intelligent asset management systems and IoT technology can not only improve the efficiency and accuracy of asset management of state-owned enterprises, but also bring more added value and competitive advantages to 177 enterprises. In addition to the steps mentioned above, here are some additional extensions: Intelligent prediction and optimization: Intelligent asset management systems combined with Internet of Things technology can use big data analysis and machine learning algorithms to achieve prediction and optimization of asset usage. Through continuous monitoring and analysis of data, the system can predict equipment failures and maintenance needs, thereby enabling preventive maintenance and reducing downtime and repair costs. Real-time monitoring and alarming: IoT devices can monitor the operating status and environmental parameters of assets in real time, and issue alarms or reminders in a timely manner. For example, the temperature, humidity, pressure and other parameters of key equipment are monitored, and alarms are automatically triggered once they exceed the set range, helping enterprises to take timely measures to avoid losses. Intelligent supply chain management: Intelligent asset management systems can be integrated with supply chain systems to achieve real-time monitoring and management of material procurement, transportation and inventory. Through IoT technology, real-time tracking of raw materials and finished products throughout the supply chain can be achieved, improving the visibility and efficiency of the supply chain. Improved resource utilization efficiency: Through real- time monitoring and analysis of asset usage, intelligent asset management systems can help enterprises optimize resource utilization and improve equipment utilization and production efficiency. For example, sensors can be installed on the production line to monitor equipment operating status and production efficiency in real time, and adjust production plans and equipment configuration in a timely manner to improve production efficiency and reduce costs. Intelligent energy management: Combined with Internet of Things technology, intelligent asset management systems can realize real-time monitoring and management of energy. By monitoring energy consumption, identifying energy waste and optimizing energy-saving measures, we help enterprises reduce energy costs and reduce environmental pollution. Inspired by these ideas, the prediction can be achieved from following aspects. And as the extended, the listed company asset forecast will be selected as the analytic scenario. In the analysis of listed companies, the prediction of fixed assets is a key task, involving important factors in the future profitability of the target company and the long-term development of the company. Regulators often closely scrutinize fixed asset forecasts, paying particular attention to the following: Asset quality and condition assessment: Regulators will carefully review the subject company’s fixed asset list and evaluate the quality and condition of the assets, including the operating status of the equipment, the maintenance of the property, etc. Fixed assets with good asset quality and well- maintained assets are more likely to bring stable profits to the company in the future. Depreciation and residual value forecast verification: The depreciation and residual value forecast of fixed assets directly affects the company's balance sheet and future profit forecast. Regulatory agencies will verify the rationality of the company's depreciation policy and residual value forecast to ensure that they are consistent with the actual situation and avoid the impact of too high or too low depreciation rates on asset values. Review of future investment plans: Regulators will review the future investment plans of the subject company, especially those related to fixed assets. A reasonable investment plan can help improve the efficiency of the use of fixed assets and reduce operating costs, thereby enhancing the profitability of the enterprise. Technology update and replacement strategy: The technical level and replacement speed of fixed assets are crucial to the competitiveness and long-term development of an enterprise. Regulatory agencies will review the company's technology renewal strategy and fixed asset replacement plan to assess the company's future competitiveness and development potential. 4. Conclusion The integration of artificial intelligence (AI) into asset management is ushering in a new era of opportunity for businesses, offering ways to improve operational efficiency, mitigate risk, and optimize resource allocation. By leveraging advanced data analytics and predictive maintenance strategies, organizations can improve decision-making, minimize downtime, and extract maximum value from their asset portfolios. The comprehensive literature review underscores the plethora of methodologies and technologies used in asset management, underscoring the need for continuous innovation and adaptability in response to evolving market dynamics. In addition, the proposed forecasting and management suggestions highlight the critical role of intelligent asset management systems and IoT technology in facilitating predictive insights and optimizing asset performance. Stringent regulatory scrutiny on asset quality, depreciation policies, and investment strategies underscores the need for transparent and prudent asset management practices. References [1] Wicaksana, Ketut Arya Bayu, I. Wayan Karman, I. M. S. A. Jaya, and I. Ariana. "Fixed Asset Applications Using Excel as a Supplement of Village Asset Management Systems." In International Conference on Science and Technology on Social Science (ICAST-SS 2020), vol. 544, pp. 28-33. Atlantis Press, 2020. [2] Konareva, P. A., and Z. I. Kruglyak. "The fixed assets management in the system 1C: ERP enterprise management." Modern Science 10 (2017): 63-66. [3] GOLOVETSKY, Nikolay Y., Elena V. IVANOVA, Elena A. GALIY, Irina B. VYPRYAZHKINA, and Olga Y. LEBEDEVA. "Improvement of methodological approaches to financial analysis of fixed assets of the enterprise." Revista Espacios 40, no. 34 (2019). [4] Saraubon, Kobkiat, Panurut Chinakul, and Rittinan Chanpen. "Asset Management System using NFC and IoT Technologies." In Proceedings of the 2019 3rd International Conference on Software and e-Business, pp. 124-128. 2019. [5] Gârleanu, Nicolae, and Lasse Heje Pedersen. "Efficiently inefficient markets for assets and asset management." The Journal of Finance 73, no. 4 (2018): 1663-1712. [6] Petchrompo, Sanyapong, Anupong Wannakrairot, and Ajith Kumar Parlikad. "Pruning Pareto optimal solutions for multi- objective portfolio asset management." European Journal of Operational Research 297, no. 1 (2022): 203-220. [7] Khoirudin, Rifki, Linda Vebriana, and Fatima Muhammad Abdulkarim. "Analysis of Optimization of Fixed Asset 178 Management for Sleman Regency Government." Journal of Asset Management and Public Economy 1, no. 1 (2022): 1-8. [8] McMahon, Paul, Tieling Zhang, and Richard Dwight. "Requirements for big data adoption for railway asset management." Ieee Access 8 (2020): 15543-15564. [9] Boyes, G. A., C. Ellul, and D. Irwin. "Exploring BIM for operational integrated asset management-a preliminary study utilising real-world infrastructure data." In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 4, no. 4W5, pp. 49-56. 2017. [10] Wang, Minli, Jie Tan, and Yaning Li. "Design and implementation of enterprise asset management system based on IOT technology." In 2015 IEEE international conference on communication software and networks (ICCSN), pp. 384-388. IEEE, 2015. [11] Rifai, Ahmad, Rida Prihatni, and Ati Sumiati. "Analysis of Financial and Non-Financial Factors on Fixed Assets Revaluation in Banking Companies." Interconnection: An Economic Perspective Horizon 1, no. 2 (2023): 87-99. [12] Zhang, Caiming, and Yang Lu. "Study on artificial intelligence: The state of the art and future prospects." Journal of Industrial Information Integration 23 (2021): 100224. [13] Briganti, Giovanni, and Olivier Le Moine. "Artificial intelligence in medicine: today and tomorrow." Frontiers in medicine 7 (2020): 509744. [14] Combi, Carlo, Beatrice Amico, Riccardo Bellazzi, Andreas Holzinger, Jason H. Moore, Marinka Zitnik, and John H. Holmes. "A manifesto on explainability for artificial intelligence in medicine." Artificial Intelligence in Medicine 133 (2022): 102423.