International Journal of Education Sciences Original Research
Building a Fair and Transparent Student Performance Predictor Using Interpretable Machine Learning
Abstract
This research incorporates a new, ethical framework that will help predict student performance based upon equitable access for all students, with a specific focus on the principles of ethics (fairness, transparency). The primary focus of this work is to use a scaled Random Forest Regressor (RFR) model to project Semester Three CGPA of MCA students, by including several different enrichment factors into a single comprehensive enriching dataset containing sem1 and sem2 GPAs, 10th and 12th percentiles, as well as additional dynamic behavioral indicators such as attendance rates and study hours, and demographic and engagement factors including gender and extracurricular activities among others. In integrating SHapley Additive exPlanations (SHAP) with an ensemble RFR model creates a combined effect of enabling the separation of the ‘black-box’ effect of the RFR model. SHAP provides mathematically sound, local, and global attribution to features to allow for the transformation of a passive predictor into a personalised, causal diagnostic tool. Additionally, the methodology utilises a specialised gender sensitivity audit that will enable organisations to identify and quantify and report potential ‘disparities’ that could occur at the group level. This satisfies the ethical requirement for equity in such organisations. The final outcome is an IML-enabled predictive system that is made available to you through a live web application. It provides not only a prediction method but also an ethical, actionable framework for higher education for the development of ethical and equitable decision-making and for providing educational interventions in the area of higher education.
Keywords
References (27)
- Breiman L. Random forests. Machine learning. 2001 Oct;45(1):5–32.
- Slack D, Hilgard A, Singh S, Lakkaraju H. Reliable post hoc explanations: Modeling uncertainty in explainability. Advances in neural information processing systems. 2021 Dec 6;34:9391–404.
- Ribeiro MT, Singh S, Guestrin C. " Why should i trust you?" Explaining the predictions of any classifier. InProceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 1135–1144).
- Albanna B, Handl J, Heeks R. Publication outperformance among global South researchers: An analysis of individual-level and publication-level predictors of positive deviance. Scientometrics. 2021 Oct;126(10):8375–431.
- Romero C, Ventura S. Educational data mining: a review of the state of the art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (applications and reviews). 2010 Jul 26;40(6):601–18.
- Romero C, Ventura S. Educational data mining and learning analytics: An updated survey. Wiley interdisciplinary reviews: Data mining and knowledge discovery. 2020 May;10(3):e1355.
- Asif R, Merceron A, Ali SA, Haider NG. Analyzing undergraduate students’ performance using educational data mining. Computers & education. 2017 Oct 1;113:177–94.
- Aldowah H, Al-Samarraie H, Fauzy WM. Educational data mining and learning analytics for 21st century higher education: A review and synthesis. Telematics and Informatics. 2019 Apr 1;37:13–49.
- Saxena M, Singh NP. Role of Hybrid Feature Selection Algorithms in Foreseeing Student Performance. Sciences (IJTNS). 2025;5(1):43–75.
- Nuankaew P, Nuankaew WS. Student Performance Prediction Model for Predicting Academic Achievement of High School Students. European Journal of Educational Research. 2022;11(2):949–63.
- Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, Katz R, Himmelfarb J, Bansal N, Lee SI. From local explanations to global understanding with explainable AI for trees. Nature machine intelligence. 2020 Jan;2(1):56–67.
- Freiesleben T, König G, Molnar C, Tejero-Cantero A. Scientific Inference with Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena: T. Freiesleben et al. Minds and Machines. 2024 Jul 15;34(3):32.
- Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D. A survey of methods for explaining black box models. ACM computing surveys (CSUR). 2018 Aug 22;51(5):1–42.
- Linardatos P, Papastefanopoulos V, Kotsiantis S. Explainable ai: A review of machine learning interpretability methods. Entropy. 2020 Dec 25;23(1):18.
- Barocas S, Hardt M, Narayanan A. Fairness and machine learning. Recommender systems handbook. 2020;1:453–9.
- Porras JM, Lara JA, Romero C, Ventura S. A case-study comparison of machine learning approaches for predicting student’s dropout from multiple online educational entities. Algorithms. 2023 Dec 3;16(12):554.
- Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A. A survey on bias and fairness in machine learning. ACM computing surveys (CSUR). 2021 Jul 13;54(6):1–35.
- Raftopoulos G, Davrazos G, Kotsiantis S. Evaluating fairness strategies in educational data mining: A comparative study of bias mitigation techniques. Electronics. 2025 May 1;14(9):1856.
- Chernozhukov V, Karl Härdle W, Huang C, Wang W. Lasso-driven inference in time and space. The Annals of Statistics. 2021 Jun;49(3):1702–35.
- James G, Witten D, Hastie T, Tibshirani R. Linear model selection and regularization. InAn introduction to statistical learning: with applications in R 2021 Jul 28 (pp. 225–288). New York, NY: Springer US.
- Van Norren DE. The ethics of artificial intelligence, UNESCO and the African Ubuntu perspective. Journal of Information, Communication and Ethics in Society. 2023 Jan 31;21(1):112–28.
- McCarthy J. Generality in artificial intelligence. Communications of the ACM. 1987 Dec 1;30(12):1030–5.
- Choi WC, Lam CT, Mendes AJ. Analyzing the interpretability of machine learning prediction on student performance using shapley additive explanations. In2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE) 2024 Dec 9 (pp. 1–8). IEEE.
- Alamri R, Alharbi B. Explainable student performance prediction models: A systematic review. Ieee Access. 2021 Feb 23;9:33132–43.
- Hoq M, Brusilovsky P, Akram B. Analysis of an explainable student performance prediction model in an introductory programming course. InProceedings of the 16th International Conference on Educational Data Mining 2023 (pp. 79–90).
- Le Quy T, Nguyen TH, Friege G, Ntoutsi E. Evaluation of group fairness measures in student performance prediction problems. InJoint European Conference on Machine Learning and Knowledge Discovery in Databases 2022 Sep 19 (pp. 119–136). Cham: Springer Nature Switzerland.
- Sahlaoui H, Nayyar A, Agoujil S, Jaber MM. Predicting and interpreting student performance using ensemble models and shapley additive explanations. IEEe Access. 2021 Oct 29;9:152688–703.