research_article September 10, 2026

Machine Learning for Early-Warning Academic Risk Prediction in Nigerian Polytechnic: A Case of Computer Engineering Program

Shehu Ibrahim GAJO
Volume1
Issue3
Pages142-150
DOI10.5281/zenodo.22722582
Abstract

Student attrition in STEM education is a persistent challenge, with Nigerian polytechnics facing additional pressures including large class sizes, limited monitoring capacity, and high engineering failure rates. Existing studies rely mainly on post-examination data and focus on university settings, overlooking the early-semester dynamics of Nigerian polytechnics. This study develops and evaluates a machine learning-based early-warning system for predicting academic risk in Nigerian polytechnic Computer Engineering programmes using early-semester indicators. A structured synthetic dataset of 2,000 student records was generated to simulate Nigerian polytechnic conditions, incorporating only Weeks 1–6 features to prevent temporal bias. Three supervised learning algorithms (Logistic Regression, Decision Tree, and Random Forest) were implemented using scikit-learn and evaluated via stratified 10-fold cross-validation using Accuracy, Precision, Recall, F1-score, and ROC-AUC metrics. Results show that early-semester indicators such as continuous assessment scores, attendance, and prior academic history provide sufficient predictive signal for reliable at-risk classification. Logistic Regression achieved the highest Recall (0.8182) and ROC-AUC (0.8276), recording the lowest false negative count (16 of 88 at-risk students missed) and is recommended as the model of choice for intervention-priority deployment. Actionable at-risk classifications are generated 9 to 12 weeks before final assessments, enabling timely academic support within existing institutional data infrastructure.

Keywords
Machine LearningEarly-Warning SystemAcademic Risk PredictionNigerian PolytechnicLogistic Regression
Download Article PDF
References
  1. Abiodun, O. J., & Wreford, A. I. (2024). Student’s Performance Evaluation Using Ensemble Machine Learning Algorithms. Engineering and Technology Journal, 09(08). https://doi.org/10.47191/etj/v9i08.23
  2. Adejo, O. W., Connolly, T., & Doyle, K. (2019). Predicting Student Academic Performance Using Multi-model Heterogeneous Ensemble Approach. Journal of Applied Research in Higher Education, 11(2), 241–254. https://doi.org/10.1108/JARHE-09-2017-0113
  3. Adekitan, A. I., & Salau, O. (2019). The Impact of Engineering Students’ Performance in the First Three Years on Their Graduation Result Using Educational Data Mining. Heliyon, 5(2), e01250. https://doi.org/10.1016/j.heliyon.2019.e01250
  4. Albreiki, B., Zaki, N., & Alashwal, H. (2021). A Systematic Literature Review of Student Performance Prediction Using Machine Learning Techniques. Education Sciences, 11(9), 552. https://doi.org/10.3390/educsci11090552
  5. Alhazmi, E., & Sheneamer, A. M. (2023). Early Predicting of Students Performance in Higher Education. IEEE Access, 11, 27579–27589. https://doi.org/10.1109/ACCESS.2023.3250702
  6. 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
  7. Balcioğlu, Y. S., & Artar, M. (2025). Predicting academic performance of students with machine learning. Information Development, 41(3), 896–915. https://doi.org/10.1177/02666669231213023
  8. Balcıoğlu, Y. S., & Artar, M. (2023). Predicting Academic Performance of Students with Machine Learning. Information Development, 41, 02666669231213023. https://doi.org/10.1177/02666669231213023
  9. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
  10. Casanova, J. R., Castro-López, A., Bernardo, A. B., & Almeida, L. S. (2023). The Dropout of First-Year STEM Students: Is It Worth Looking beyond Academic Achievement? Sustainability, 15(2), 1253. https://doi.org/10.3390/su15021253
  11. Casanova, J. R., Vasconcelos, R., Bernardo, A. B., & Almeida, L. S. (2021). University Dropout in Engineering: Motives and Student Trajectories. Psicothema, 33(4), 595–601. https://doi.org/10.7334/psicothema2020.363
  12. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7
  13. Hussain, M., Zhu, W., Zhang, W., Abidi, S. M. R., & Ali, S. (2019). Using Machine Learning to Predict Student Difficulties from Learning Session Data. Artificial Intelligence Review, 52(1), 381–407. https://doi.org/10.1007/s10462-018-9620-8
  14. Quinlan, J. R. (1993). C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers.
  15. Rastrollo-Guerrero, J. L., Gómez-Pulido, J. A., & Durán-Domínguez, A. (2020). Analyzing and Predicting Students’ Performance by Means of Machine Learning: A Review. Applied Sciences, 10(3), 1042. https://doi.org/10.3390/app10031042
  16. Saito, T., & Rehmsmeier, M. (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLOS ONE, 10(3), e0118432. https://doi.org/10.1371/journal.pone.0118432
  17. UNESCO. (2021). Rethinking Education: Towards a Global Common Good? United Nations Educational, Scientific and Cultural Organization. https://www.unesco.org/en/education
  18. Villar, A., & De 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
  19. Waheed, H., Hassan, S.-U., Aljohani, N. R., Hardman, J., Alelyani, S., & Nawaz, R. (2020). Predicting Academic Performance of Students from VLE Big Data Using Deep Learning Models. Computers in Human Behavior, 104, 106189. https://doi.org/10.1016/j.chb.2019.106189
  20. World Bank. (2020). The Human Capital Project: Educating for the Future—STEM and Skills for Development. The World Bank Group. https://www.worldbank.org/en/topic/education
  21. Xiao, F. & others. (2021). A Four-Phase, Ten-Step EDM Process for Educational Data Analytics. Journal of Educational Data Mining, 13(1), 1–30.
  22. Yağcı, M. (2022). Educational Data Mining: Prediction of Students’ Academic Performance Using Machine Learning Algorithms. Smart Learning Environments, 9(1), 11. https://doi.org/10.1186/s40561-022-00192-z
Scroll to Top