Predicting Student Performance Using a Hybrid Model Based on Machine Learning and Feature Selection Techniques

Abstract

Accurately predicting student performance plays a critical role in modern educational institutions. It enables targeted interventions and enhances educational outcomes. This paper proposes a hybrid predictive model for predicting student performance employing feature selection based on standard deviation filtering, coupled with machine learning techniques. In the machine learning phase used Decision Tree (DT), Random Forest (RF), K-Nearest Neighbours (KNN), and Support Vector Machines (SVM) were used. The proposed model is tested and evaluated over the Student Performance Prediction—Multiclass Case dataset. The experimental result demonstrated robust predictive capabilities, with Decision Tree models showing the highest accuracy at 100%. KNN and Naive Bayes (NB) also exhibited strong performances, achieving accuracy rates of 98.98% and 96.94%, respectively. This work underscores the importance of selecting appropriate features and machine learning algorithms to optimise student performance prediction, significantly benefiting early identification of at-risk students.