Cover
Volume 7, Special Issue 4 (2026)

Published: August 25, 2026

Pages: 28-36

Research Article

Machine learning-based prediction and behavioral analysis of student academic performance using educational and digital learning features

Sozan S. Haydar Ali 1 Azad A. Saeed 1 Soran H. Mohamad 1
1Department of Statistics and Informatics, Collage of Administration and Economics, Sulamani University, Kurdistan Region, Iraq
History
  • Received: June 13, 2026
  • Available Online: August 25, 2026
DOI

https://doi.org/10.56967/ejfb2026915

Abstract

This study presents a machine learning-based framework for predicting and analyzing student academic performance using behavioral, psychological, demographic, and digital learning features. The dataset consists of 14,003 student records collected from higher education institutions in 2024 and obtained from Kaggle. It includes 16 variables covering study behaviors, engagement patterns, learning resources, psychological factors, and demographic characteristics. The target variable (response) was Final Grade, which was categorized into four performance levels: Low / Fail / Poor performance, below average performance, Good / Average performance, and Excellent / High performance, representing overall academic performance. Three machine learning algorithms XGBoost (Extreme Gradient Boosting), CatBoost (Categorical Boosting), and Support Vector Machine (SVM) were applied to classify student performance levels. The models were evaluated using confusion matrices, accuracy, F1-score, MCC, R², RMSE, MAE, and feature importance analysis. Results show that XGBoost achieved the highest performance (99.96% accuracy), followed by CatBoost (99.82%) and SVM (98.96%). Analysis of the importance analysis revealed that Exam Score is the most influential predictor across all models. The study highlights the effectiveness of advanced machine learning techniques in predicting academic success and supporting data-driven educational decision-making.

Keywords

References

  1. Abdulla, S. H., & Mohamad, S. H. (2024). Comparing and Evaluating Machine Learning Techniques for Liver-Hydatid-Cyst Classification. Al-Anbar University Journal of Economic & Administration Sciences, 16(4).‏
  2. Adilshamim8. (2024). Student Performance and Learning Style Dataset. Kaggle. https://www.kaggle.com/datasets/adilshamim8/student-performance-and-learning-style/data
  3. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
  4. Hussein, M. M. F., Mohamad, S. H., & Qadir, B. H. (2024). Machine Learning Approaches to Classify and Predict Congenital Jaundice. Khazayin of Economic and Administrative Sciences, 52-64.‏
  5. Mohamad, S. H. (2025). Machine Learning Classification Methods Performance Comparison in Liver Cancer Cohort. Al-Furat Journal of Innovations in Management Sciences, 1(1), 1-11.‏
  6. Mohamad, S. H., & Hussein, M. M. F. (2024). Diagnosing Anemia Disease using Partial Least Square (PLS) Models and Support Vector Machines (SVM). Journal of Kurdistani for Strategic Studies, 2(9).‏
  7. Najem, K., Ziti, S., & Zaoui Seghroucheni, Y. (2025). Student Performance and Learning Behavior Dataset for Educational Analytics. Zenodo. https://doi.org/10.5281/zenodo.16459132
  8. Omer, A., Faraj, S. M., & Mohamad, S. H. (2023). An application of two classification methods: hierarchical clustering and factor analysis to the plays PUBG. Iraqi Journal of Statistical Sciences, 20(1), 25-42.‏
  9. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31, 6638–6648.
  10. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31, 6638–6648.
  11. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.