DESIGNING AND IMPLEMENTING AN ADAPTIVE SYSTEM BASED ON ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR ADAPTING INDIVIDUAL TEACHING STRATEGIES IN HIGHER EDUCATION INSTITUTIONS: METHODOLOGY, ARCHITECTURE, AND EXPERIMENTAL VALIDATION

Authors

  • Safarova Sitora Toshpulatovna Master's Student, Asia International University Author

Keywords:

artificial intelligence, adaptive learning, machine learning, individual learning strategies, Random Forest, XGBoost, Bayesian Knowledge Tracing, VARK model, higher education, intelligent tutoring system, PostgreSQL, AI in education.

Abstract

This article presents the methodology, platform architecture, and experimental validation of an adaptive system based on artificial intelligence (AI) and machine learning (ML) designed to adapt individual teaching strategies in higher education institutions. The system analyzes students' knowledge levels, learning styles, cognitive characteristics, and learning behavior in real time to automatically select the optimal teaching strategy for each student. The research was conducted with 186 second-year students from three academic programs at Bukhara State University using a quasi-experimental pretest-posttest control group design. A four-component adaptive model (Student Model, Knowledge Model, Pedagogical Model, Adaptive Strategy Module) was developed, identifying 5 strategy types (Scaffolding, Blended, Self-directed, Remediation, Enrichment). A three-tier platform architecture (React frontend, FastAPI backend, PostgreSQL + Redis) was built on 10 technological components. During the 4-month experimental trial, 76,800 activity records were collected from 94 students in the experimental group, and 12 primary parameters were expanded to 30 features through feature engineering. Four ML algorithms (Random Forest, XGBoost, KNN, MLP) were optimized through 85 hyperparameter combinations and 5-fold stratified cross-validation. Experimental validation showed that the AI-based adaptive system demonstrated statistically significant superiority over traditional teaching methods.

References

1. Decree of the President of the Republic of Uzbekistan No. PF-6079 dated October 5, 2020, "On Measures for the Development of the Digital Economy in the Republic of Uzbekistan." https://lex.uz/docs/5031048

2. Resolution of the President of the Republic of Uzbekistan No. PQ-4996 dated February 17, 2021, "On Measures for the Implementation of Artificial Intelligence Technologies." https://lex.uz/docs/5297051

3. Resolution of the President of the Republic of Uzbekistan No. PQ-4479 dated October 8, 2019, "On Additional Measures for Improving the Quality of Education in Higher Education Institutions." https://lex.uz/docs/4545887

4. Russell S., Norvig P. (2021). Artificial Intelligence: A Modern Approach. 4th Edition. Pearson.

5. Woolf B.P. (2009). Building Intelligent Interactive Tutors: Student-Centered Strategies for Revolutionizing E-Learning. Morgan Kaufmann. DOI: 10.1016/B978-0-12-373594-2.X0001-1

6. Brusilovsky P., Millán E. (2007). User Models for Adaptive Hypermedia and Adaptive Educational Systems. In: The Adaptive Web. Springer. DOI: 10.1007/978-3-540-72079-9_1

7. Popenici S., Kerr S. (2017). Exploring the Impact of Artificial Intelligence on Teaching and Learning in Higher Education. RPTEL, 12(1), 22. DOI: 10.1186/s41039-017-0062-8

8. Johnson L. et al. (2015). NMC Horizon Report: 2015 Higher Education Edition. The New Media Consortium.

9. Ali R., Magliaro S. (2020). Effectiveness of Adaptive Learning Systems in Higher Education. Journal of Educational Technology, 48(3), 112–128.

Downloads

Published

2026-06-09