Prediction of Student Academic Performance Using a Multi-Regression and Classification-Based Model

Abstract

The Prediction of students’ performance is a necessity because it forecasts how well a student is expected to perform during a course of study. Over the years, studies have revealed that student performance has been below average, with one of the main causes being that a thorough prediction of a student's academic potential is typically not done. To choose the best model for predicting and categorizing academic achievement, a multi-regression analysis is performed using machine learning models such as Decision Tree, K-Nearest Neighbor, Random Forest, Logistic Regression, and Support Vector Machine. Furthermore, the result shows that Random Forest is the best-performing classifier in this study, with an F1 score and accuracy of 94.9%, as well as the best-performing regression model, with a Mean Absolute Error (MAE) of 0.3711 in predicting academic success.