توسعه چارچوب مبتنی بر الگوریتمهای یادگیری ماشین برای بهینه‌سازی پیش‌بینی هزینه‌های سازمانی
محورهای موضوعی : علم اطلاعات
1 - Department Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran
کلید واژه: : پیش‌بینی هزینه‌های سازمانی, یادگیری ماشین, مدل داده‌محور, بهینه‌سازی منابع, تحلیل داده‌ها, رگرسیون خطی, مدیریت مالی,
چکیده مقاله :
چکیده : در دنیای امروز، پیش‌بینی دقیق هزینه‌های سازمانی برای بهینه‌سازی تخصیص منابع و افزایش بهره‌وری، یکی از چالش‌های اصلی مدیران به شمار می‌رود. تغییرات سریع اقتصادی و پیچیدگی فزاینده فرآیندهای مالی، ضرورت استفاده از روش‌های پیش‌بینی داده‌محور را بیش از پیش برجسته کرده است. این پژوهش چارچوبی مبتنی بر الگوریتمهای یادگیری ماشین ارائه می‌دهد که هدف آن بهبود دقت پیش‌بینی هزینه‌های سازمانی و تسهیل برنامه‌ریزی مالی دقیق‌تر در سازمان‌ها است. در این مطالعه، داده‌های واقعی مالی و عملیاتی از سازمان بیمه سلامت در یک بازه زمانی پنج‌ساله جمع‌آوری و پس از انجام مراحل پیش‌پردازش، برای آموزش مدل‌های پیش‌بینی به‌کار گرفته شد. مدل اصلی مورد استفاده در این پژوهش، رگرسیون خطی بوده و عملکرد آن با استفاده از معیارهایی نظیر ضریب تعیین، میانگین خطای مطلق و ریشه میانگین مربعات خطا ارزیابی شده است. نتایج این تحقیق نشان می‌دهد که مدل رگرسیون خطی توانسته است با دقت بالایی تغییرات هزینه‌های سازمانی را پیش‌بینی کرده و عوامل کلیدی مؤثر بر هزینه‌ها را شناسایی کند. چارچوب پیشنهادی این مطالعه می‌تواند به سازمان‌ها در بهبود برنامه‌ریزی بودجه، مدیریت منابع مالی و کاهش خطاهای پیش‌بینی کمک کند. علاوه بر این، یافته‌های تحقیق حاضر، پایه‌ای علمی برای توسعه مدل‌های پیش‌بینی در سایر حوزه‌های سازمانی فراهم می‌آورد و امکان ارتقای تصمیم‌گیری‌های استراتژیک را برای مدیران تسهیل می‌کند.
Abstract:
In today's world, accurately predicting organizational costs to optimize resource allocation and enhance productivity is one of the key challenges faced by managers. Rapid economic changes and the increasing complexity of financial processes have further highlighted the necessity of data-driven forecasting methods. This study presents a machine learning-based framework aimed at improving the accuracy of organizational cost prediction and facilitating more precise financial planning in organizations.
In this research, real financial and operational data from the Health Insurance Organization over a five-year period were collected and, after preprocessing, used to train predictive models. The primary model employed in this study is linear regression, and its performance was evaluated using metrics such as the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE).
The results demonstrate that the linear regression model can accurately predict variations in organizational costs and identify key factors influencing expenses. The proposed framework can assist organizations in improving budget planning, financial resource management, and reducing prediction errors. Furthermore, the findings of this research provide a scientific foundation for developing predictive models in other organizational domains, facilitating more informed strategic decision-making for managers
منابع
1. Abdulla, A., Naim, A., Muniasamy, A., Mohammed, A. B., Bilfaqih, S. M., & Sabahath, A. (2025). Optimizing Business Insights Data Visualization Applications in Sales Forecasting, Marketing Analytics, and Financial Reporting. In Data Visualization Tools for Business Applications (pp. 103-124). IGI Global.
2. Krylov, S. (2025). Theory and Practice of Target Financial Forecasting at Company Level. In Encyclopedia of Information Science and Technology, Sixth Edition (pp. 1-34). IGI Global.
3. Tang, J. W., Yuan, Q., Zhang, L., Marshall, B. J., Tay, A. C. Y., & Wang, L. (2025). Application of machine learning-assisted surface-enhanced Raman spectroscopy in medical laboratories: principles, opportunities, and challenges. TrAC Trends in Analytical Chemistry, 118135.
4. Lucasius, C., Ali, M., Patel, T., Kundur, D., Szatmari, P., Strauss, J., & Battaglia, M. (2025). A procedural overview of why, when and how to use machine learning for psychiatry. Nature Mental Health, 1-11.
5. Mukherjee, R., Ghosh, A., Chakraborty, C., De, J. N., & Mishra, D. P. (2025). Rice leaf disease identification and classification using machine learning techniques: A comprehensive review. Engineering Applications of Artificial Intelligence, 139, 109639.
6. Arpita, H. D., Al Ryan, A., Hossain, M. F., Rahman, M. S., Sajjad, M., & Prova, N. N. I. (2025). Exploring Bengali speech for gender classification: machine learning and deep learning approaches. Bulletin of Electrical Engineering and Informatics, 14(1), 328-337.
7. Cohen, S. (2025). The evolution of machine learning: Past, present, and future. In Artificial Intelligence in Pathology (pp. 3-14). Elsevier.
8. Lee, G. F. (1991). Alternative liability insurance: A physician-owned captive insurance company. American journal of obstetrics and gynecology, 164(6), 1680-1685.
9. Prymostka, O. (2018). Life insurance companies marketing strategy in the digital world. Insurance Markets and Companies, 9(1), 66-73.
10. Jiang, W., & Wong, J. K. (2016). Key activity areas of corporate social responsibility (CSR) in the construction industry: a study of China. Journal of cleaner production, 113, 850-860.
11. Yitbarek, B. (2020). State Regulation and Supervision of Insurance Industry in Ethiopia: The Need for a Separate Regulatory and Supervisory Body. Master of Laws (LL. M) thesis, Addis Ababa University School of Graduate Studies Faculty of law, 11.
12. Ta, N. (2024). Analysis of the Development Status of Foreign Insurance Companies in China. International Journal of Global Economics and Management, 2(2), 194-199.
13. Weng, D. Y. (2000). China's life insurance industry: opportunities and challenges for foreign companies (Doctoral dissertation, Massachusetts Institute of Technology).
14. Koprolcec, M., Greger, K., Pirc, A., & Moro, M. (2009). Insurance of assets as a risk in wood sector/Osiguranje imovine kao rizik u poslovanju drvnog sektora. Drvna Industrija, 60(4), 235-244.
15. Zhi, Y., & Hu, J. L. (2011). A cross-strait comparative study of efficiency of life insurance companies: An application of the input slack adjustment approach. African Journal of Business Management, 5(14), 5746.
16. Wong, J. (2002). A comparison of solvency requirements and early warning systems for life insurance companies in China with representative world practices. North American Actuarial Journal, 6(1), 91-112.
17. Kong, Y. H., & Chen, S. Y. (2016). A Study on Development Strategies of Professional Internet Insurance Company: Comparative Analysis on Key financial indicators of Online & Offline Insurance Companies. In Proceedings of the 7th China International Conference on Insurance and Risk Management (pp. 295-307).
18. Koller, M. (2012). Stochastic models in life insurance. Springer Science & Business Media.
19. Sun, L., & Huang, Y. (2016). Measuring the instability of China’s financial system: Indices construction and an early warning system. Economics, 10(1), 20160019.
20. Přečková, L., & Vávrová, E. (2019). The Expense Ratio Development of Insurance Portfolios in Selected Insurance Companies in the Czech Republic in 2010-2017. In European Financial Systems 2019: Proceedings of 16th Annual International Scientific Conference on European Financial Systems (pp. 452-461).
21. Adıgüzel, Z. (2019). Analysis of the effects of corporate image on purchasing behaviors in insurance companies. International Journal of Eurasia Social Sciences.
22. Zhu, J., & Shu, G. An Empirical Analysis of Small and Medium-sized China’s Insurance Industry's Core Competitiveness by Three-stage DEA Method.
23. Ramakrishnan, S., Alsahliy, D. K., Hishan, S. S., Keong, L. B., & Vaicondam, Y. (2017). Corporate responsibility of the listed Malaysian insurance companies. Advanced Science Letters, 23(9), 9279-9281.
24. Vintilă, A., Trucmel, I. M., & Roman, M. D. (2022). Measuring and Analyzing the Efficiency of Firms in the Insurance Industry Using DEA Techniques. Journal of Social and Economic Statistics, 11(1-2), 59-83.
25. Jinga, D. T. Understanding the New International Financial Reporting Standards: The Case of IFRS 17.
26. Nissim, D. (2010). Analysis and valuation of insurance companies. CE| ASA (Center for Excellence in Accounting and Security Analysis) Industry Study, (2).
27. Zhang, F., Han, L., & Zhang, J. (2016). The Analysis of Property Insurance Company's Profitability and its Impact Factor. In Proceedings of 7th China International Conference on Insurance and Risk Management (CICIRM). Xi’an. China (pp. 235-248).
28. Zhi, Y., & Hu, J. L. (2011). A cross-strait comparative study of efficiency of life insurance companies: An application of the input slack adjustment approach. African Journal of Business Management, 5(14), 5746.