Training an artificial intelligence model to predict subject-specific educational outcomes

Objective. The study aims to identify the relationship between the quality of education in general educational institutions and students' cognitive and personality traits, as well as parameters of the educational environment, with the goal of developing a tool for forecasting and adjusting subject-specific learning outcomes.
Method. Based on surveys of participants in the educational process at the online school «Dom Znaniy» (House of Knowledge), a database comprising over 1.3 million records across 315 parameters was compiled. After filtering, 218 significant indicators were retained. An original iterative method utilizing neural networks was applied to restore missing data, and a novel approach based on decision trees was proposed for vectorizing categorical features. An artificial neural network was trained on data from 2022–2023 to forecast subject learning outcomes.
Results. A neural network was developed capable of predicting students' subject-specific results for the upcoming academic year with an error margin of less than four percent. All 218 parameters were ranked by their influence on academic performance, and the quantitative relationship of each parameter to the final grade was established. A user interface was created enabling parents to simulate changes in educational environment parameters and a child's personal characteristics to achieve target educational outcomes.
Conclusion. The proposed approach enables a transition from reactive, exam-focused preparation for state final certification to proactive management of the educational trajectory, resulting in a 10-point increase in the average Unified State Exam (USE) score. Future development of the project includes automating parameter collection using artificial intelligence technologies.

1. Aslanov T.G., Abidova M.Sh., Maksudov M.M., Tagirov Kh.Yu., Magomed M.M. The prototype of the system for the formation of an individual learning path. Herald of Daghestan State Technical University. Technical Sciences. 2023;50(2):35-40. (In Russ..) DOI: 10.21822/2073-6185-2023-50-2-35-40.

2. Rory J., Gray G. Prediction of student academic performance using Moodle data from a Further Education setting // Irish Journal of Technology Enhanced Learning. 2019. 5(1) P. 1-19. DOI: 10.22554/ijtel.v5i1.57.

3. Prasertisirikul P., Laohakiat S., Trakunphutthirak R., Sukaphat S. A Predictive Model for Student Academic Performance in Online Learning System. In: 2022 International Conference on Digital Government Technology and Innovation (DGTi-CON). Bangkok, Thailand. 2022;76-79. DOI: 10.1109/DGTi-CON53875.2022.9849205.

4. Efremov S.K., Nesterenko I.S., Epifantseva V.A., Anisimov S.L., Pechenin E.A. Using an artificial neural network to predict student performance. Bulletin of the Voronezh Institute of the Federal Penitentiary Service of Russia. 2025;15(1):49-55. (In Russ)

5. omaschenko A.I., Scherbin S.I., Kharitonov I.M., Panfilov A.E., Zharavin N.S. The use of statistical machine learning methods to predict the future academic performance of university applicants. Modern High Technologies. 2025;23(9):132-136. (In Russ.) DOI: 10.17513/snt.40497.

6. Philippou N., Ajoodha R., Jadhav A. Using Machine Learning Techniques and Matric Grades to Predict the Success of First Year University Students. In: 2020 2nd International Multidisciplinary Information Technology and Engineering Conference (IMITEC). Kimberley, South Africa. 2020;1-5. DOI: 10.1109/IMITEC50163.2020.9334087.

7. Martinho V. R. D. C., Nunes C., Minussi C.R. An Intelligent System for Prediction of School Dropout Risk Group in Higher Education Classroom Based on Artificial Neural Networks. In: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence. Herndon, VA, USA. 2013;159-166. DOI: 10.1109/ICTAI.2013.33.

8. Ranawaka U.M., Rajapakse C. Predicting examination performance using machine learning approach: A case study of the Grade 5 scholarship examination in Sri Lanka. In: 2020 International Research Conference on Smart Computing and Systems Engineering (SCSE). Colombo, Sri Lanka. 2020;202-209. DOI: 10.1109/SCSE49731.2020.9313029.

9. Kharitonov I.M., Krushel E.G., Privalov O.O., Stepanchenko I.V., Stepanchenko O.V. Higher school education quality forecasting by regression analysis methods. Proceedings of the Saint Petersburg State Institute of Technology (Technical University). 2021;56(82):72-80. (In Russ.) DOI: 10.36807/1998-9849-2020-56-82-72-80.

10. Zhu W. High school student GPA prediction by various linear regression models. Theoretical and Natural Science. 2024;52(1):153-162. DOI: 10.54254/2753-8818/52/2024ch0136.

11. Dolganov D. N. Model assessment and prediction of academic success. Bulletin of Experimental Education. 2018;1(14):40-54. (In Russ)

12. Pobedinskaya T.V., Zaslavskaya O.Yu. The use of machine learning algorithms to prediction the performance of basic school students. Moscow State Pedagogical University Bulletin. Series: Informatics and Education Digitalization. 2022. 62(4):75-82. (In Russ) DOI: 10.25688/2072-9014.2022.62.4.06.

13. Slabchenko O., Sydorenko V., Siebert X. Development of models for imputation of data from social networks on the basis of an extended matrix of attributes. Eastern-European Journal of Enterprise Technologies. 2016;4(2(82)):24-34. DOI: 10.15587/1729-4061.2016.74871.

14. Saini P., Nagpal B. Analysis of missing data and comparing the accuracy of imputation methods using wheat crop data. Multimedia Tools and Applications. 2023; 82. DOI: 10.1007/s11042-023-17178-9.

15. Cortese F. P., Pievatolo A. Statistical jump model for mixed-type data with missing data imputation. Advances in Data Analysis and Classification. 2025;19. DOI: 10.1007/s11634-025-00631-y.

16. Fabrikant M. S. Model-oriented approach to missing values: multiple imputation in multilevel regression using R (on the example of analyzing survey data). Sociology: Methodology, Methods, Mathematical Modeling. 2015;24(41:7-29. (In Russ) EDN: WITRUD.

17. Palchevsky E.V. Method for Improving the Accuracy of Predictive Values of Time Series Based on the Imputation of Historical Data.Programmnaya Ingeneria.2023;14(6):301-306.DOI:10.17587/prin14.301-306.

18. Chernavin P.F., Chernavin F.P., Chernavin N.P., Ponomareva O.A., Salnik K.D. Experience in applying various data imputation methods in solving classification problems. Herald of Computer and Information Technologies. 2024; 21(6(240)):50-57. (In Russ) DOI: 10.14489/vkit.2024.06.pp.050-057.

19. Losev A. S., Massel A. G. Time series forecasting and data imputation for the digital twin of a solar power plant. Information and Mathematical Technologies in Science and Management. 2022;7(1(25)): 91-101. (In Russ) DOI: 10.38028/ESI.2022.25.1.008.

20. Aslanov T.G., Aygumov T.G. Simulation of the operation of bottom seismographs using artificial neural networks. Marine Intellectual Technologies.2022;15(2-1(56)):143-148. (In Russ) DOI:10.37220/MIT.2022.56.2.019

21. Parameters of the educational process influencing subject learning outcomes [File]// Online school "Dom Znaniy" (House of Knowledge), 12.08.2022. https://docs.domznaniy.school/1.jpg (Accessed: 12.01.2026)

22. Alexandrov I.A., Kirichek A.V., Kuklin V.Z., Chervyakov L.M. Development of an Algorithm for Multicriteria Optimization of Deep Learning Neural Networks. HighTech and Innovation Journal. 2023;4(1):157-173. DOI: 10.28991/HIJ-2023-04-01-011.

23. Forecasting a child's academic performance one year ahead, featuring the child's and teacher's personal dashboards as well as a parent's dashboard with the ability to modify certain previously entered parameters. Presentation of the online school "Dom Znaniy" (House of Knowledge) system operation, 11.09.2025. URL: https://cms.domznaniy.school/uploads/Prognozirovanie1_821b7ceb67.pptx (Accessed: 12.01.2026)

24. Alexandrov I.A., Kuklin V.Zh., Muranov A.N., Tatarkanov A.A. Theoretical Foundations of an Algorithm of Visualization of a Set of Points of a Multidimensional Space for Use in Anthropotechnical Decision Support Systems. Proceedings of the Institute for System Programming of the RAS. 2022; 34(4):201-210. DOI 10.15514/ISPRAS-2022-34(4)-14.

25. Alexandrov I.A. Principles of technological preparation automation of production by neural network modeling. Inzhenernyj vestnik Dona. 2019;5(56):22.