Prediction of Student Academic Performance Using Machine Learning

Predicting student academic performance is important for improving learning outcomes and providing timely academic support.Traditional evaluation methods often fail to identify students who may struggle at an early stage.This study presents a machine learning-based approach to predict student performance using historical academic data.Supervised learning algorithms such as Linear Regression, Logistic Regression, Decision Tree, and Random Forest are applied and compared.Data preprocessing techniques including cleaning, feature selection, and normalization are used to enhance model performance.The models are evaluated using accuracy, precision, recall, F1-score, and confusion matrix.Results show that ensemble-based algorithms achieve better prediction accuracy.The proposed approach can help educational institutions identify at-risk students early and take appropriate academic interventions.