Predicting Student Academic Performance Using Machine Learning Algorithms: A Comparative Study on the StudentsPerformance Dataset

Academic performance prediction is a vital application of machine learning in educational data mining, enabling early intervention for at-risk students and supporting data-driven institutional policies. This paper presents a comparative analysis of supervised machine learning algorithms applied to the StudentsPerformance dataset containing 1000 student records. The study implements K-Nearest Neighbors (KNN), Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM) models for binary classification of student performance. The methodology includes data preprocessing, feature engineering, label encoding, feature scaling, train-test splitting, and model evaluation using accuracy and cross-validation techniques. Results demonstrate high predictive accuracy, with KNN, Logistic Regression, and SVM achieving 100% test accuracy, while Random Forest and Decision Tree also performed exceptionally well. The research highlights the effectiveness of machine learning in educational data mining and emphasizes explainable AI techniques such as feature importance analysis and decision tree visualization to improve trust and interpretability in academic prediction systems.