An Explainable Hybrid Machine Learning Framework for Student Profiling and Feature Attribution in Mathematics Achievement: Analysis of Cambodian High Schools

Source abstract

n recent years, the application of machine learning in education has gained significant attention for its potential to uncoverhidden patterns and improve student learning outcomes. This study employs a hybrid unsupervised-supervised machine learningapproach to achieve two primary objectives: first, to uncover hidden learning profiles of Cambodian high school students, and second,to identify and validate the most significant factors contributing to their mathematics achievement. Using a dataset of 7,188 students,a two-phase analytical pipeline integrating unsupervised and supervised learning was developed. In the first phase, k-modes and k-prototypes clustering were applied with multiple internal validation and stability metrics to analyze latent student profiles. Thisexploratory phase informed a the second phase using CatBoost, Decision Tree, and Random Forest classifiers, with featuresignificance determined through a consensus of Mean Decrease in Impurity (MDI), Permutation Feature Importance (PFI), andRecursive Feature Elimination (RFE) metrics. Results indicate that k-prototypes produced a superior two-cluster solution (stabilityscore: 0.9941) compared to k-modes (0.1181), segmenting students primarily by math anxiety, grade level. Supervised modelingidentified previous semester math achievement, anxiety, and grade level as the most stable predictive features, with the core featureset achieving a cross-validation accuracy of 0.7068. The integrated analytical framework successfully translated computationalmetrics into actionable educational insights, providing a validated, data-driven foundation for targeted intervention strategies tosupport mathematics learning in Cambodian high schools.