Improving Student Performance Prediction using Artificial Intelligence

Abstract

In recent years, improvements in predicting student performance have garnered significant attention due to their applications in education, personalized academ- ic support, and optimizing educational resources. Predicting student outcomes using artificial intelligence (AI) holds immense potential for teachers to proac- tively identify and support at-risk students. In this thesis, we explore this excit- ing field by employing various machine learning algorithms with an enhanced approach to model optimization. Specifically, we implement hyperparameter tuning using grid search to ensure optimal configurations for four classifiers: Support Vector Machines (SVM), Multilayer Perceptrons (MLP), Decision Trees, and Artificial Neural Networks (ANNs). This comprehensive analysis aims to identify the most effective model for predicting student performance in the selected dataset. The results reveal that the Artificial Neural Network model achieved an accuracy of 98%, demonstrating its superiority in performance pre- diction.