An Explainable AI-Driven Predictive Analytics Framework for Student Academic Performance Assessment and Personalized Learning Optimization

Authors

  • Prof. Seema Sharma

Abstract

The increasing adoption of digital learning environments has generated substantial educational data that can be leveraged to understand student learning behaviour and improve academic outcomes. However, conventional student performance prediction approaches often rely on machine learning models that provide limited interpretability and offer insufficient support for personalized learning interventions. The proposed framework integrates machine learning algorithms with Explainable Artificial Intelligence (XAI) techniques to predict student academic performance, identify influential learning factors, and generate personalized recommendations for improving learning outcomes. The framework considers multiple academic and behavioural attributes, including attendance, assessment scores, assignment completion, learning engagement, study patterns, and historical academic performance. Predictive models are employed to classify and estimate student performance levels, while explainability techniques such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations) are incorporated to interpret model predictions and identify the contribution of individual features. Based on the prediction outcomes and explanatory insights, the framework aims to identify students who may require additional academic support and facilitate targeted learning recommendations. The proposed approach emphasizes prediction accuracy, model transparency, and actionable educational insights, addressing the limitations of traditional black-box prediction systems. By combining predictive analytics with interpretable machine learning, this research establishes a foundation for intelligent and adaptive educational support systems that can assist educators in data-driven decision-making and promote personalized learning experiences.

References

[1] C. Romero and S. Ventura, “Educational Data Mining: A Review of the State of the Art,” IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 40, no. 6, pp. 601–618, 2010, doi: 10.1109/TSMCC.2010.2053532.

[2] S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems 30 (NeurIPS), 2017.

[3] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–1144, doi: 10.1145/2939672.2939778.

[4] B. Mallikarjun Rao and B. V. Ramana Murthy, “Prediction of Student’s Educational Performance Using Machine Learning Techniques,” Advances in Intelligent Systems and Computing, vol. 1079, pp. 429–440, 2020, doi: 10.1007/978-981-15-1097-7_36.

[5] V. K. Yarram, S. K. Parimi, R. Cherukuri, and B. Jegajothi, “Intelligent Web based Student Performance Prediction using Machine Learning in Java,” in 2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 2025, pp. 591–598, doi: 10.1109/ICAAIC64647.2025.11331046.

[6] Z. Khoudi, N. Hafidi, M. Nachaoui, and S. Lyaqini, “New Approach to Enhancing Student Performance Prediction Using Machine Learning Techniques and Clickstream Data in Virtual Learning Environments,” SN Computer Science, vol. 6, art. 139, 2025, doi: 10.1007/s42979-024-03622-6.

Downloads

Published

2026-06-20

Issue

Section

Articles