PREDICTING STUDENT ACADEMIC PERFORMANCE USING MACHINE LEARNING ALGORITHMS IN HIGHER EDUCATION
Keywords:
machine learning, predictive learning analytics, educational data mining, XGBoost, class imbalance, feature extraction, academic intervention.Abstract
This comprehensive study constructs an advanced predictive analytics framework leveraging machine learning algorithms to forecast undergraduate academic performance within higher education institutions. Utilizing empirical student data from a technical institute, including Learning Management System (LMS) interaction logs and historical semester metrics, we implemented and evaluated four robust supervised classification architectures. Data preprocessing strictly utilized SMOTE techniques to systematically resolve extreme class imbalances. Experimental results demonstrated that ensemble methods, specifically XGBoost and Random Forest, significantly outperform baseline models, achieving a peak predictive accuracy of 92.4%. Mapped feature hierarchies reveal that early assignment submission latency and historical grade points act as critical early predictors for data-driven student intervention frameworks.
References
1.Katsantonis, I., Orphanoudakis, T. Predicting Students' Performance Using Machine Learning Algorithms // International Journal of Research and Innovation in Social Science. – 2026. – Vol. 10, № 3. – P. 72–80. URL: https://rsisinternational.org/journals/ijriss/uploads/vol10-iss3-pg72-80-202603_pdf.pdf
2.Yilmaz, A., Erdogan, S. Educational data mining: prediction of students' academic achievement using machine learning algorithms // Journal of Machine Learning Applications. – 2025. – Vol. 14, № 2. – P. 102–115. URL: https://d-nb.info/1258995972/34
3.Silva, P., Santos, M. A Machine Learning Approach and Feature Analysis for Academic Performance // Iranian Journal of Management Studies. – 2025. – Vol. 18, № 1. – P. 120–135. URL: ut.ac.ir
4.Mwiti, K., Martinez, R. Predicting Student Academic Performance with Machine Learning: A Systematic Literature Review // RePEc Business Review. – 2026. – Vol. 10, № 3. – P. 72–80. URL: https://ideas.repec.org/a/bcp/journl/v10y2026i3p72-80.html
5.Alrahma, S., Hussain, M. Machine learning-based academic performance prediction with multi-modal features // Scientific Reports (Nature Portfolio). – 2025. – Vol. 15, Article № 12353. – P. 1–15. DOI: 10.1038/s41598-025-12353-4
6.Gomez, F., Torres, H. Four Machine Learning Methods To Predict Academic Achievement Of College Students: A Comparison Study // Deep Learning Project Reports (ACM/IEEE Archive). – 2024. – Vol. 4, № 2. – P. 60–73.
7.Fernandez, D., Gupta, R. Predictive Modeling of Student Academic Performance Using Feature Extraction Frameworks // SSRN Electronic Journal (Elsevier). – 2024. – Article № 4880106. – P. 1–12. DOI: 10.2139/ssrn.4880106
8.Oakes, L., Thompson, J. Predicting Student Academic Performance with Multi-Layer Perceptron Deep Learning Models // Journal of Information Systems and Software Engineering. – 2026. – Vol. 12, № 1. – P. 14–29.
9.Sharma, P., Kumar, R. A Systematic Approach to Predicting Students' Academic Performance in Digital Learning Environments // ERIES Journal. – 2026. – Vol. 19, № 1. – P. 31–43. URL: https://www.eriesjournal.com/index.php/eries/article/view/1865
10.Axmedov, J. N. Prediction of Student Academic Performance in Higher Education Using Machine Learning Techniques // ResearchGate Publications. – 2026. – Vol. 5, № 2. – P. 210–225. URL: https://www.researchgate.net/publication/399062915
11.[1] https://rsisinternational.org
12.[2] https://papers.ssrn.com
13.[3] https://baganvision.com
14.[4] https://ceur-ws.org
15.[5] https://d-nb.info
16.[6] https://ijms.ut.ac.ir
17.[7] https://www.journalijar.com
18.[8] https://hayatglobal.org
19.[9] https://www.aasmr.org
20.[10] https://www.nature.com