MODELING OF AN ADAPTIVE EDUCATIONAL SYSTEM BASED ON MACHINE LEARNING ALGORITHMS

The rapid transition to digital education has revealed the fundamental limitations of linear, «conveyor belt» platforms that offer identical content to all learners. Such systems are unable to take into account individual differences in initial training levels, cognitive styles, learning speeds, and content format preferences, which reduces the overall effectiveness of learning. This article addresses this problem by developing and describing a formalized mathematical model of an adaptive educational system. The proposed approach is based on a vector representation of both the learner and the learning materials in a single multidimensional feature space. The central element of the model is an interpretable utility function (U), which evaluates and selects the optimal next learning module for a specific student in real time. The function finds a balance between several pedagogically significant criteria: potential knowledge gain (G), cognitive load (E), and format compliance (M). A key feature is the built-in machine learning mechanism (online learning), which iteratively updates the learner's knowledge vector based on their results, allowing the system to continuously adapt. To validate the model, a numerical experiment was conducted, which confirmed that the system is capable of making non-trivial choices, finding the optimal balance between all factors, and correctly tracking the learner's progress. Thus, the proposed model represents a transparent and flexible framework for creating a new generation of intelligent learning systems capable of building truly personalized and effective educational trajectories.

1. Müller W. Understanding intention and use of digital elements in higher education teaching / W. Müller, M. Leyer // Education and Information Technologies. – 2023. – Vol. 28. – Р. 15571-15597. https://doi.org/10.1007/s10639-023-11798-2.

2. Comparative analysis of frequently used e-learning platforms / S. Jain et al // Frontiers in Education. – 2024. – № 9. – Р. 1431531. https://doi.org/10.3389/feduc.2024.1431531.

3. The Book Theme Based Personalized Recommendation using Reinforcement Learning / Т. Mandel et al // Proceedings of the 23rd International Conference on Intelligent User Interfaces. – 2018. – Р. 545-550.

4. Serdyukov P. Formalism in online education / P. Serdyukov // Journal of Research in Innovative Teaching & Learning. – 2021. – № 14(2). – Р. 118-132. https://doi.org/10.1108/JRIT-02-2021-0010.

5. Serdyukov P. Challenging Formalization in Education and Beyond: Problems and Solutions for Traditional and Online Learning (1st ed.) / P. Serdyukov // Routledge. – 2022. https://doi.org/10.4324/9781003290094.

6. Alenezi M. Digital Learning and Digital Institution in Higher Education / M. Alenezi // Education Sciences. – 2023. – № 13(1). – Р. 88. https://doi.org/10.3390/educsci13010088.

7. Review of Group Formalism for Automated Formalization in Mechanical Engineering / K.B. Moulya и др. // Proceedings of the 6th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV). – 2025. – Р. 1744-1753. https://doi.org/10.1109/ICICV64824.2025.11086060.

8. Hypothesis Formalization: Empirical Findings, Software Limitations, and Design Implications / Е. Jun et al // ACM Transactions on Computer-Human Interaction. – 2022. – № 29(1), Article 6, 28 pages. https://doi.org/10.1145/3476980.

9. Boufim M. Digital Marketing: Five Stages Maturity Model for Digital Marketing Strategy Implementation / M. Boufim, H. Barka // International Journal of Business and Technology Studies and Research. – 2021. – № 3(3). – Р. 15. https://doi.org/10.5281/zenodo.5578706.

10. Kabulov A. Mathematical model of Information Processing in the Ecological Monitoring Information System / A. Kabulov, I. Yarashov // 2021 International Conference on Information Science and Communications Technologies (ICISCT). – 2021. – Р. 1-4. https://doi.org/10.1109/ICISCT52966.2021.9670192.

11. Formalizing Trust in Artificial Intelligence / A. Jacovi et al // Prerequisites, Causes and Goals of Human Trust in AI. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT '21). – 2021. – Р. 624-635. https://doi.org/10.1145/3442188.3445923.

12. Digital Twins: A Maturity Model for Their Classification and Evaluation / J.-F. Uhlenkamp et al // IEEE Access. – 2022. – № 10. – Р. 69605-69635. https://doi.org/10.1109/ACCESS.2022.3186353.