MODELING AND FORECASTING STUDENT PERFORMANCE IN EDUCATIONAL INFORMATION SYSTEMS USING MACHINE LEARNING METHODS

The article discusses modern approaches to modeling and predicting student academic performance dynamics in educational systems using machine learning methods. The study includes a detailed analysis of existing methodological approaches, ready-made solutions, and commercial platforms; a review of literature sources describing the application of data analysis algorithms in the educational field; and the development of a custom model that covers data collection, processing, model and algorithm selection, and prediction of student performance.
Various popular ready-made solutions and commercial platforms that use machine learning methods to analyze, predict, and optimize educational processes have been examined, including: Blackboard Predict, Civitas Learning, Knewton Adaptive Learning Platform, DreamBox Learning, IBM Watson Education, and SAS Campus Analytics. The study analyzed the weights of general attributes that affect prediction, and examined how specific features influence outcomes.
The presented article demonstrates that the use of neural networks can significantly improve prediction accuracy, making them a valuable tool for managing educational institutions and making timely administrative decisions. However, one drawback of this algorithm is its long training time on computers with lower computational capabilities. Therefore, other algorithms were also considered during the development of the custom model.
The research results showed that ensemble methods significantly reduced prediction errors compared to linear regression, while also requiring much less time for training and forecasting.

1. Johnson A. Predictive Analytics in Education: Regression Models and Decision Trees / A. Johnson, B. Smith, C. Thompson // Journal of Educational Data Science. – 2015. – № 10(2). – Р. 115-132.

2. Lee S. Machine Learning Approaches for Student Performance Prediction / S. Lee, H. Kim // International Journal of Learning Analytics. – 2016. – № 8(1). – Р. 45-60.

3. Ivanov I.I. Primenenie metodov analiza dannykh v obrazovanii / I.I. Ivanov, P.P. Petrov // Vestnik obrasovatel'nykh issledovanij. – 2017. – № 4. – Р. 34-50.

4. Kumar R. Ensemble Methods for Forecasting in Education / R. Kumar, P. Rao // Computational Education Research. – 2018. – № 7(3). – Р. 142-157.

5. Singh D. Enhancing Predictive Accuracy with Random Forests in Educational Data / D. Singh, M. Patel // Advances in Educational Computing. – 2019. – № 12(4). – Р. 89-104.

6. Zhang Y. Gradient Boosting for Educational Forecasting / Y. Zhang, X. Li, M. Wang // IEEE Transactions on Education. – 2020. – № 63(2). – Р. 128-137.

7. Chen L. Deep Learning in Higher Education: A Survey / L. Chen, H. Zhang, Y. Liu // Journal of Educational Technology. – 2017. – № 14(3). – Р. 75-92.

8. Garcia M. Neural Networks for Student Engagement Analysis / M. Garcia, F. Martinez // Computers Education. – 2018. – № 120. – Р. 45-59.

9. Thompson R. Explainable AI in Education: Interpreting Deep Learning Models / R. Thompson, D. Johnson, J. Lee // Educational Data Mining Journal. – 2019. – № 9(2). – Р. 105-121.

10. Lee J. Interpretability of Neural Networks in Predictive Education Analytics / J. Lee // IEEE Access. – 2020. – № 8. – Р. 22345-22354.

11. White R. Data Quality in Educational Research: Issues and Solutions / R. White, E. Brown // International Journal of Educational Data Management. – 2016. – № 5(1). – Р. 67-82.

12. Aleksandrova M. Metody korreljacionnogo analiza v obrazovanii / M. Aleksandrova, A. Sidorov, O. Nikolaeva // Zhurnal prikladnoj statistiki. – 2018. – № 6(2). – Р. 94-110.

13. Smirnov D.L. Problemy ochistki i normalizatsii dannych v obrazovatel'nom analize / D.L. Smirnov // Izvestia vuzov. – 2017. – № 3. – Р. 56-69.

14. Kuznetcov V.V. Otbor priznakov v obrazovatel'nyh dannykh: teoreticheskie i prakticheskie aspekty / V.V. Kuznetcov // Nauchnyj vestnik obrazovaniya. – 2018. – № 2. – Р. 78-92.

15. Brown T. Optimizing Resource Allocation in Education Through Predictive Analytics / T. Brown, S. Wilson, K. Martin // Educational Management Review. – 2018. – № 11(3). – Р. 135-151.

16. Walker P. Strategic Planning in Education Using Machine Learning / P. Walker // Journal of Educational Policy. – 2019. – № 15(1). – Р. 49-66.

17. Petrova E.S. Primenenie metodov mashinnogo obucheniya dlya optimizatcii obrazovatel'nych program / E.S. Petrova // Obrazovatel'nye technologii segodnya. – 2019. – № 7. – Р. 88-104.

18. Nikolaev S.V. Prognozirovanie dinamiki obrazovatel'nych sistem na osnove bol'shikh dannykh / S.V. Nikolaev // Zhurnal innovacionnykh issledovanij v obrazovanii. – 2020. – № 5. – Р. 120-136.

19. Jones M. Comparative Analysis of Educational Forecasting Methods / M. Jones // Computers in Human Behavior. – 2016. – № 55. – Р. 234-241.

20. Miller S. Evaluating Predictive Models in Education: A Comparative Study / S. Miller // Journal of Learning Analytics – 2017. – № 4(2). – Р. 101-117.

21. Chen Z. Hybrid Models for Forecasting Student Performance / Z. Chen, Q. Li // IEEE Transactions on Learning Technologies. – 2018. – № 11(3). – Р. 158-168.

22. Zhao Y. Integrative Approaches to Educational Data Mining / Y. Zhao, W. Huang, F. Xu // International Journal of Educational Technology in Higher Education. – 2019. – № 16(1). – Р. 66-80.

23. Civitas Learning. Civitas Learning – Student Success Platform [Электронный ресурс]. – Режим доступа: https://www.civitaslearning.com (дата обращения: 21.10.2025).

24. A Method for Prediction and Analysis of Student Performance That Combines Multi-Dimensional Features of Time and Space / Zheng Luo et al // Journals Mathematics. – 2024. – Vol. 12? Issue 22. – H/ 3597. https://doi.org/10/3390/math12223597.

25. Vaarma M. Predicting student dropouts with machine learning: An empirical study in Finnish higher education / M. Vaarma, H. Li. // Journal Technology in Society. – 2024-03. – Vol. 76. – Article number 102474. – Р. 1-10.