Predicting Students' Academic Performance Using Machine Learning: A Comparative Analysis Based on Subject Marks

This research project investigates the prediction of students’ academic performance using machine learning techniques based on subject marks in Mathematics, Physics, and Chemistry. Four classification algorithms, namely Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine, are evaluated using accuracy, precision, recall, F1-score, and five-fold cross-validation. The study also analyzes subject-wise distributions, correlations, model performance, and feature importance. The deposited file contains the final research paper describing the dataset, methodology, implementation, experimental results, limitations, and future scope.