Personalized Course Recommendation System for Nigerian Secondary School Students Using Supervised Machine Learning Approach

The high-rate diversity of courses offered in higher institutions has provided students with a broad spectrum of options and a desire for academic and career development. However, this abundance of choice has also introduced significant challenges in selecting courses that align with students' interests, skills, and long-term career goals. Traditional academic advisory systems which rely heavily on one-on one guidance from counselors or faculty, are constrained by the availability of advisors, the time required to provide tailored guidance, and the lack of data-driven insights into students' unique preferences and abilities. This paper presents a machine learning based personalized course recommendation system designed to assist students in selecting appropriate educational courses based on their Unified Tertiary Matriculation Examination (UTME) scores. Leveraging a comprehensive dataset of 1,000 students, the system employs advanced machine learning techniques, notably the XGBoost classifier, combined with Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. Extensive feature engineering transforms raw examination scores and demographic variables into predictive features, enhancing model accuracy. The model was rigorously evaluated using stratified train-test splits and multiple performance metrics, achieving an overall accuracy exceeding 99%. Key insights include high predictive power of subject streams and individual subject scores in forecasting suitable courses for the students. Resulting recommendations provide actionable, interpretable guidance for students and counselors, facilitating informed decision-making and optimized academic pathways. This research demonstrates that machine learning models significantly enhance personalized learning experiences by effectively predicting suitable courses for students and also contributes a robust, datadriven methodology for educational planning support.

Personalized course recommendation, Supervised Learning, XGBoost

1. Bucad, A. T. (2024). Towards the Development of a Career Path Recommender System for Senior High School in Selected Public Schools using Multi-Label Classification. International Journal of Research and Innovation in Applied Science, 9(3), 374-382. [Google Scholar] [Crossref]

2. Devika, P., & Milton, A. (2025). Book recommendation using sentiment analysis and ensembling hybrid deep learning models. Knowledge and Information Systems, 67(2), 1131-1168. [Google Scholar] [Crossref]

3. Drushchak, N., Tyshchenko, V., & Polyakovska, N. (2025). Towards Responsible AI in Education: Hybrid Recommendation System for K-12 Students Case Study. In 2025 IEEE/ACM International Workshop on Responsible AI Engineering (RAIE) (pp. 61-68). IEEE. [Google Scholar] [Crossref]

4. Dubey, K. P., Gupta, N. K., & Sharma, A. (2024). Performance Prediction Data Mining System for Disabled Students Using Machine Learning. Fusion: Practice & Applications, 15(2). [Google Scholar] [Crossref]

5. Feng, R., & Luo, J. (2025). Analysis of K-12 teachers’ demand characteristics for digital educational resource services from the perspective of adaptive feedback: Based on the analysis of KANO model. Education and Information Technologies, 30(4), 4695-4716. [Google Scholar] [Crossref]

6. Iorzua, J. T., Moses, T., Eke, C. I., Agushaka, O. J., Kwaghtyo, D. K., & Godswill, T. (2025). A Machine Learning Based Approach to Course and Career Recommendation System: A Systematic Literature Review. Journal of Computing Theories and Applications, 3(1), 1-16. [Google Scholar] [Crossref]

7. Ju, C., Cao, J., Yang, Y., Yang, Z. Q., & Lee, H. M. (2023, December). Heterogeneity-aware cross-school electives recommendation: a hybrid federated approach. In 2023 IEEE International Conference on Data Mining Workshops (ICDMW) (pp. 1500-1508). IEEE. [Google Scholar] [Crossref]

8. Liu, M., & Yu, D. (2023). Towards intelligent E-learning systems. Education and Information Technologies, 28(7), 7845-7876. [Google Scholar] [Crossref]

9. Meenakshi, G. (2012). Multi source feedback based performance appraisal system using Fuzzy logic decision support system. arXiv preprint arXiv:1203.1882. [Google Scholar] [Crossref]

10. Mishra, P. (2025). Revolutionizing education with AI and ML. Internet of Behavior-Based Computational Intelligence for Smart Education Systems, 53-94. [Google Scholar] [Crossref]

11. Naseer, F., Khan, M. N., Tahir, M., Addas, A., & Aejaz, S. H. (2024). Integrating deep learning techniques for personalized learning pathways in higher education. Heliyon, 10(11). [Google Scholar] [Crossref]

12. Nnodi J.T & Okoro E.O (2025): Leveraging Machine Learning for Predicting Climate Change Impacts on Agricultural Productivity in Bayelsa State, Nigeria: A Pathway to Sustainable Solutions. University of Ibadan Journal of Science and Logics in ICT Research 14(1), pp. 172 - 187. [Google Scholar] [Crossref]

13. Nwelih, E., & Eguavoen, V. O. (2025). Enhancing Smart Education: Comparative Analysis of Hybrid Recommendation Algorithms For Personalized Learning. Quantum Journal of Engineering, Science and Technology, 6(1), 125-132. [Google Scholar] [Crossref]

14. Qassem, A. M. A., & Idrees, A. M. (2025). Leveraging Artificial Intelligence to Recommend Personalized Learning Pathways: A Case Study on Secondary Education Students. Journal of Mathematics and Statistics Studies, 6(4), 01-16. [Google Scholar] [Crossref]

15. Rahman, M. M., Aziz, N., Yeasmin, F., & Khan, Y. (2025, June). Personalized Elective Course Recommendation Using Content-Based Filtering. In 2025 International Conference on Circuit, Systems and Communication (ICCSC) (pp. 1-6). IEEE. [Google Scholar] [Crossref]

16. Saroja, K. B., & Suvitha, V. (2025). Analysis of Markovian queueing model with two phase of services, single and multiple working vacations and customer balking. International Journal of Mathematics in Operational Research, 32(3), 277-293. [Google Scholar] [Crossref]

17. Tang, Q. (2023). Resource recommendation in e-learning platforms based on knowledge graph (Doctoral dissertation, Université de Technologie de Compiègne). [Google Scholar] [Crossref]

18. Taylor, R., Fakhimi, M., Ioannou, A., & Spanaki, K. (2025). Personalized learning in education: a machine learning and simulation approach. Benchmarking: An international journal, 32(7), 2662-2689. [Google Scholar] [Crossref]

19. Tudor, I., Dlab, M. H., & Hoić-Božić, N. (2025). Personalized Learning in Secondary and Higher Education: A Systematic Literature Review of Technology-Enhanced Approaches. International journal of educational methodology, 11(3), 359-375. [Google Scholar] [Crossref]

20. Wang, D., Lian, D., Xing, Y., Dong, S., Sun, X., & Yu, J. (2022). Analysis and prediction of influencing factors of college student achievement based on machine learning. Frontiers in Psychology, 13, 881859. [Google Scholar] [Crossref]

21. Wu, S., Cao, Y., Cui, J., Li, R., Qian, H., Jiang, B., & Zhang, W. (2024). A comprehensive exploration of personalized learning in smart education: From student modeling to personalized recommendations. arXiv preprint arXiv:2402.01666. [Google Scholar] [Crossref]

22. Xin, X., Shu-Jiang, Y., Nan, P., ChenXu, D., & Dan, L. (2022). Review on A big data-based innovative knowledge teaching evaluation system in universities. Journal of innovation & knowledge, 7(3), 100197. [Google Scholar] [Crossref]

23. Yu, C., & Yao, G. (2024). Enhancing student engagement with ai-driven personalized learning systems. International Transactions on Education Technology (ITEE), 3(1), 1-8. [Google Scholar] [Crossref]

• Travaalay: An AI-Powered Mobile Platform for Tourism with Student Translator Guides, Agro-Tourism, and Astro-Tourism Experiences
• Integrating QVoC (QR Code with Voice Content) to Enhance Medication Adherence for Geriatric Diabetic Patients
• "Navigating Global Volatility: Assessing the Resilience and Innovation of Bahrain’s Financial Sector Through the 2025 Financial Stability Report"
• Comparison of Similarity Distance-Based Metrics for HODA and BANGLA Dataset for Enhanced Precision
• Stereo Matching Frameworks for Depth-Aware Object Detection: A Comprehensive Review