This paper presents a comparative analysis of machine learning algorithms for student performance prediction using academic and behavioral factors such as attendance, study hours, internal marks, and previous results. Predicting student outcomes at an early stage helps educational institutions identify weak students and provide timely academic support. The study evaluates commonly used classification algorithms including Decision Tree, Random Forest, Logistic Regression, and Naive Bayes. The models are compared based on prediction accuracy, efficiency, and suitability for educational datasets. Among the evaluated methods, ensemble techniques such as Random Forest demonstrate better overall performance due to improved generalization and reduced overfitting. The proposed approach highlights the importance of machine learning in educational data mining and decision-making systems. Student performance prediction can help improve academic planning, increase pass rates, and support personalized learning strategies in modern institutions.
UA et al. (Mon,) studied this question.