This research presents a comparative study of machine learning algorithms for predicting student academic performance using the StudentsPerformance dataset. The study evaluates K-Nearest Neighbors (KNN), Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM) classifiers on a binary Pass/Fail prediction task. A structured pipeline involving feature engineering, preprocessing, feature scaling, hyperparameter tuning, and cross-validation was implemented. Experimental results demonstrate excellent predictive performance, with KNN, Logistic Regression, and SVM achieving 100% test accuracy. Explainable AI techniques including Random Forest feature importance and Decision Tree decision-path analysis were used to improve model transparency and interpretability. The findings highlight the effectiveness of machine learning and explainable AI in educational data mining and student performance prediction.
Yashaswi A R (Sun,) studied this question.