A Hybrid Explainable AI Model for Accurate andTransparent Prediction of Student AcademicPerformance

Abstract

Predicting student academic performance accurately is essential and allows for timely interventions and datasupported educational decision-making. However, the black-box nature of state-of-the-art machine learning modelshinders their use in policy-sensitive educational settings, where interpretability and accountability are paramount. Wepropose a structured hybrid explainable artificial intelligence (XAI) framework that combines three tree-based ensemblemodels–namely, random forest, XGBoost, and CatBoost–using a prediction-level soft-voting strategy and couples themwith complementary post-hoc interpretation methods at the explanation level (SHAP and LIME). Instead of proposing anew base algorithm, this study systematically unifies heterogeneous boosting and bagging approaches with strictvalidation as well as dual-layer explanation consistency evaluation. Experiments on the UCI Student Performancedataset show that the proposed framework can achieve a competitive predictive performance (91.8% accuracy, ROC–AUC = 0.953) together with transparent and actionable interpretability. The robustness of the interpretability layer isfurther supported by a quantitative assessment of explanation stability, fidelity, and agreement across various methods.The presented framework harmonizes the trade-off between accuracy and interpretability to provide a deployable,policy-aware decision-support solution that is aligned with responsible AI principles for adoption within educationalcontexts.