Early Warning System for Student Academic Risk Prediction Using Gradient Boosting with SMOTE-Based Class Balancing

Abstract

This study proposes a machine learning-based Early Warning Academic System for predicting student academic risk levels using historical academic performance data from ITB Indonesia. The aim of this research is to identify at-risk students at an early stage using routinely collected academic indicators, including Quiz Score, Attendance, Assignment Score, and Midterm Score. The proposed framework integrates Gradient Boosting as the classification model, Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance, and Stratified 5-Fold Cross Validation to ensure robust performance evaluation. The model classifies students into three categories, namely Safe, Warning, and Risk. Experimental results show that the proposed model achieves an accuracy of 80.00%, macro F1-score of 78.24%, Cohen’s Kappa of 0.6306, and Matthews Correlation Coefficient of 0.6311, indicating strong and reliable predictive performance under imbalanced data conditions. ROC-AUC analysis further confirms strong discriminative capability, particularly for identifying Risk students. Feature importance analysis reveals that Midterm Score is the most influential predictor (43.49%), followed by Quiz Score (25.60%) and Assignment Score (21.99%), while Attendance contributes 8.93%. These findings indicate that academic performance indicators, especially midterm assessments, play a critical role in early risk detection. The results demonstrate that effective early warning prediction can be achieved using a limited set of routinely available academic variables, providing a practical and scalable approach to support early intervention strategies in higher education institutions.

REFERENCES

Akello, E. F., Ijiga, O. M., & Idoko, I. P. (2026). Sequence-Aware Learning Analytics for Early Identification of At-Risk Academic Trajectories in Higher Education Using Transformer Models. International Journal of Innovative Science and Research Technology, 818. https://doi.org/10.38124/ijisrt/26jan563

Albreiki, B., Habuza, T., & Zaki, N. (2023). Extracting topological features to identify at-risk students using machine learning and graph convolutional network models. International Journal of Educational Technology in Higher Education, 20(1), 23. https://doi.org/10.1186/s41239-023-00389-3

Almalawi, A., Soh, B., Li, A., & Samra, H. (2024). Predictive Models for Educational Purposes: A Systematic Review. Big Data and Cognitive Computing, 8(12), 187. https://doi.org/10.3390/bdcc8120187

Alomari, S. A., Aldiabat, K., Hashim, F. A., Zitar, R. A., Liu, Z., Migdady, H., Hu, G., Smerat, A., & Abualigah, L. (2025). Supervised Learning: Teaching Machines with Labeled Data. In L. Abualigah, Mastering the Minds of Machines (1st ed., pp. 26–33). CRC Press. https://doi.org/10.1201/9781003516385-4

Aluso, L., & Enyejo, J. O. (2025). Using XGBoost and Time-Series Forecasting to Predict Student Academic Trajectories in Educational Analytics Platforms. International Journal of Innovative Science and Research Technology, 143. https://doi.org/10.38124/ijisrt/25dec159

Angeioplastis, A., Aliprantis, J., Konstantakis, M., & Tsimpiris, A. (2025). Predicting Student Performance and Enhancing Learning Outcomes: A Data-Driven Approach Using Educational Data Mining Techniques. Computers, 14(3), 83. https://doi.org/10.3390/computers14030083

Aslam, Z., Missen, M. M. S., Ghaffar, A. A., Mehmood, A., Villar, M. G., Alvarado, E. S., & Ashraf, I. (2025). Advancing fake news combating using machine learning: A hybrid model approach. Knowledge and Information Systems, 67(12), 12137–12177. https://doi.org/10.1007/s10115-025-02588-y

Bagawade, R. P., & Thirupurasundari. (2025). Ensemble Machine Learning Techniques. International Journal of Emerging Technology and Advanced Engineering, 15(4), 15–23. https://doi.org/10.46338/ijetae0425_02

Călin, S. (2025). Handling Imbalanced Data: The SMOTE Technique. 2025 17th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), 1–5. https://doi.org/10.1109/ECAI65401.2025.11095450

Charaya & Sonia. (2026). Towards Accurate Student Performance Prediction: An Assessment of Machine Learning Models and Metrics. International Journal of Latest Technology in Engineering Management & Applied Science, 15(1), 600–610. https://doi.org/10.51583/IJLTEMAS.2026.150100053

Chukwura. (2023). A comparative study of several classification metrics and their performances on data. World Journal of Advanced Engineering Technology and Sciences, 8(1), 308–314. https://doi.org/10.30574/wjaets.2023.8.1.0054

Elreedy, D., Atiya, A. F., & Kamalov, F. (2024). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning, 113(7), 4903–4923. https://doi.org/10.1007/s10994-022-06296-4

Ersozlu, Z., Taheri, S., & Koch, I. (2024). A review of machine learning methods used for educational data. Education and Information Technologies, 29(16), 22125–22145. https://doi.org/10.1007/s10639-024-12704-0

Ganage, S. S. (2026). Machine Learning Techniques for Student Performance Prediction and Academic Analytics. International Journal of Engineering Research and Science & Technology, 22(1(S)), 311–314. https://doi.org/10.62643/ijerst.2026.v22.i1(S).2064

Ge, X., Fang, C., Li, X., Sun, W., Wu, D., Zhai, J., Lin, S.-W., Zhao, Z., Liu, Y., & Chen, Z. (2025). Machine Learning for Actionable Warning Identification: A Comprehensive Survey. ACM Computing Surveys, 57(2), 1–35. https://doi.org/10.1145/3696352

Giap, N., Nghiem, T. L., Ngo, T. H., Nguyen, M. T. L., & Phung, H. Q. (2024). Increment of Academic Performance Prediction of At‐Risk Student by Dealing With Data Imbalance Problem. Applied Computational Intelligence and Soft Computing, 2024(1), 4795606. https://doi.org/10.1155/2024/4795606

Idhmad, A., Kaicer, M., Nejjar, C., & Benjouad, A. (2024). Intelligent Bankruptcy Prediction Models Involving Corporate Governance Indicators, Financial Ratios and SMOTE. Indonesian Journal of Electrical Engineering and Informatics (IJEEI), 12(1), 233–244. https://doi.org/10.52549/ijeei.v12i1.5241

Kaban, R., Rachman, A. I., Sari, I. P., Zulherry, A., Basri, M., Fadilah, N., Maulidiyah, N., Sembiring, D. J., Pratama, G. U., Ronal, R., & others. (2026). Pengantar Artificial Intelligence, Machine Learning, dan Big Data. Yayasan Kita Menulis.

Kabumba, R. K., Mbayandjambe, A. M., Tashev, T., Slavov, V., Kambale, W. V., Ngoie, R.-B. M., Kyamakya, K., & Kasereka, S. K. (2025). Predictive Modeling of Academic Success Using Machine Learning: A Comparative Analysis with SMOTE-Based Class Balancing. Procedia Computer Science, 272, 242–250. https://doi.org/10.1016/j.procs.2025.10.202

Li, G., & Sheng, H. (2025). A hybrid machine learning framework for predicting aircraft scaled sound pressure levels: A comparative study. Journal of Engineering and Applied Science, 72(1), 163. https://doi.org/10.1186/s44147-025-00714-9

Ling, Q. (2023). Machine learning algorithms review. Applied and Computational Engineering, 4(1), 91–98. https://doi.org/10.54254/2755-2721/4/20230355

Liu, H. (2025). Machine Learning Approaches for Predicting and Intervening in Students’ Academic Status. Applied and Computational Engineering, 183(1), 102–109. https://doi.org/10.54254/2755-2721/2025.BJ27254

Lokanan, M. (2024). Exploring Resampling Techniques in Credit Card Default Prediction. In Review. https://doi.org/10.21203/rs.3.rs-4087259/v1

Lu, X. (2024). Modern Education: Advanced Prediction Techniques for Student Achievement Data. International Journal of Advanced Computer Science and Applications, 15(1). https://doi.org/10.14569/IJACSA.2024.01501126

Lünich, M., Keller, B., & Marcinkowski, F. (2024). Fairness of Academic Performance Prediction for the Distribution of Support Measures for Students: Differences in Perceived Fairness of Distributive Justice Norms. Technology, Knowledge and Learning, 29(2), 1079–1107. https://doi.org/10.1007/s10758-023-09698-y

Mujahid, M., Kına, E., Rustam, F., Villar, M. G., Alvarado, E. S., De La Torre Diez, I., & Ashraf, I. (2024). Data oversampling and imbalanced datasets: An investigation of performance for machine learning and feature engineering. Journal of Big Data, 11(1), 87. https://doi.org/10.1186/s40537-024-00943-4

Nafea, A. A., Mishlish, M., Haban Shaban, A. M., AL-Ani, M. M., Alheeti, K. M. A., & Mohammed, H. J. (2023). Enhancing Student’sPerformance Classification Using Ensemble Modeling. Iraqi Journal for Computer Science and Mathematics, 4(4). https://doi.org/10.52866/ijcsm.2023.04.04.016

Nguyen, C., Thi Tran, T., Thanh Thi Nguyen, T., Ha Thi Nguyen, T., Astarkhanova, T. S., Van Vu, L., Tai Dau, K., Nguyen, H. N., Pham, G. H., Nguyen, D. D., Prakash, I., & Pham, B. (2024). Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam. Journal of Hydroinformatics, 26(1), 72–87. https://doi.org/10.2166/hydro.2023.327

Osborne, J. B., & Lang, A. S. I. D. (2023). Predictive Identification of At-Risk Students: Using Learning Management System Data. Journal of Postsecondary Student Success, 2(4), 108–126. https://doi.org/10.33009/fsop_jpss132082

Ozyurt, O., Ozyurt, H., & Mishra, D. (2023). Uncovering the Educational Data Mining Landscape and Future Perspective: A Comprehensive Analysis. IEEE Access, 11, 120192–120208. https://doi.org/10.1109/ACCESS.2023.3327624

Pan, J., Zhao, Z., & Han, D. (2025). Academic Performance Prediction Using Machine Learning Approaches: A Survey. IEEE Transactions on Learning Technologies, 18, 351–368. https://doi.org/10.1109/TLT.2025.3554174

Paul, C., & Devi, A. (2025). AI-Driven Early Warning Systems for Dropout Risk and Passed-Out Prediction in Higher Education. In Dr. Mohd. A. Gandhi, Dr. A. Dutt, Dr. V. Saravanan, & K. T. Umare (Eds.), AI, Machine Learning, and IoT Applications for Academic Performance Prediction, Faculty Well-Being, and Educational Outcomes in Higher Education (2025th ed., pp. 89–110). RADemics Research Institute. https://doi.org/10.71443/9789349552258-04

Rahmi, N. A., Defit, S., & Okfalisa. (2024). Enhancing Classification Performance: A Study on SMOTE and Ensemble Learning Techniques. 2024 International Conference on Future Technologies for Smart Society (ICFTSS), 63–68. https://doi.org/10.1109/ICFTSS61109.2024.10691339

Rajasekhar, C., & Fernandes, A. S. H. D. (2026). Student Performance Prediction Using Machine Learning and Deep Learning. In R. Shanthi, Artificial Intelligence–Driven Intelligent Learning Systems for Language Proficiency, Student Success, and Well-Being in Higher Education (2026th ed., pp. 275–297). RADemics Research Institute. https://doi.org/10.71443/9789349552401-12

Rakitin, I. V., Rakitina-Qureshi, E. V., Arabadzhieva-Kalcheva, N. A., Todorova, M. P., Penev, I. P., & Petrova, D. I. (2025). Predicting Student Placement Status Using Tree-Based Ensemble Classifiers: A Comparative Analysis of Random Forest and Gradient Boosting Models. 2025 International Conference Automatics and Informatics (ICAI), 53–58. https://doi.org/10.1109/ICAI67591.2025.11325082

Rawat, B., & Pant, H. (2025). Boosting vs. Traditional Algorithms for Student Performance Prediction. 2025 International Conference on Sustainable Communication Networks and Application (ICSCN), 1998–2003. https://doi.org/10.1109/ICSCN67106.2025.11308228

Rico-Juan, J. R., Cachero, C., & Macià, H. (2024). Study regarding the influence of a student’s personality and an LMS usage profile on learning performance using machine learning techniques. Applied Intelligence, 54(8), 6175–6197. https://doi.org/10.1007/s10489-024-05483-1

Rochmadi, T. (2025). Addressing Class Imbalance in Predicting Student Academic Outcomes: A Comparative Study of Resampling Techniques with Machine Learning Classifiers in Higher Education. Artificial Intelligence in Learning, 1(3), 211–227. https://doi.org/10.63913/ail.v1i3.32

Sathvik & Nagaveni Biradar. (2025). Student Performance Detection Using Machine Learning Techniques. International Research Journal on Advanced Engineering Hub (IRJAEH), 3(09), 3513–3516. https://doi.org/10.47392/IRJAEH.2025.0516

Sharanya, B. (2024). An Efficient Ensemble Machine Learning Model for Cardiovascular Disease Prediction Using Digital Health Records. International Journal for Research in Applied Science and Engineering Technology, 12(3), 2598–2609. https://doi.org/10.22214/ijraset.2024.58888

Sharma, Y. P., & Sasikala, K. (2026). Early Warning Systems for Student Dropout Risk Prediction. In R. Shanthi, Artificial Intelligence–Driven Intelligent Learning Systems for Language Proficiency, Student Success, and Well-Being in Higher Education (2026th ed., pp. 298–321). RADemics Research Institute. https://doi.org/10.71443/9789349552401-13

Sujon, K. M., Hassan, R., Khairudin, A. R., Moi, S. H., Mohd Shafie, M. L., Saringat, Z., & Erianda, A. (2024). The Effects of Imbalanced Datasets on Machine Learning Algorithms in Predicting Student Performance. JOIV : International Journal on Informatics Visualization, 8(3–2), 1599. https://doi.org/10.62527/joiv.8.3-2.2449

Teresa, & et. al. (2025). Predictive Modelling of Student Outcomes Using Ensemble Regression and Classification Methods. https://doi.org/10.5281/ZENODO.17599070

Tiwari, M., & Jain, N. (2024). STUDENT PERFORMANCE PREDICTION USING MACHINE LEARNING ALGORITHMS. ShodhKosh: Journal of Visual and Performing Arts, 5(6). https://doi.org/10.29121/shodhkosh.v5.i6.2024.4552

Villar, A., & Andrade, C. R. V. (2024). Supervised machine learning algorithms for predicting student dropout and academic success: A comparative study. Discover Artificial Intelligence, 4(1), 2. https://doi.org/10.1007/s44163-023-00079-z

Yu, L., Zhao, X., Huang, J., Hu, H., & Liu, B. (2023). Research on Machine Learning with Algorithms and Development. Journal of Theory and Practice of Engineering Science, 3(12), 7–14. https://doi.org/10.53469/jtpes.2023.03(12).02

Yuningsih, L., Pradipta, G. A., Hermawan, D., Ayu, P. D. W., Hostiadi, D. P., & Huizen, R. R. (2023). IRS-BAG-Integrated Radius-SMOTE Algorithm with Bagging Ensemble Learning Model for Imbalanced Data Set Classification. Emerging Science Journal, 7(5), 1501–1516. https://doi.org/10.28991/ESJ-2023-07-05-04