Predicting Students’ Academic Performance in School Education Using Classification Techniques

Abstract

In today’s scenario, data mining finds application across various domains, serving to derive insightful analyses. One the main domain in data mining is education to analyze the students’ performance and their results. Through data mining, educational institutions can assess student achievements and make policies to enhance them further. Often referred to as Educational Data Mining (EDM), this practice focuses on predicting student performance and devising measures to boost academic success. The main aim of this study was the prediction of students’ learning habits and steps that could be taken to improve students’ performance. In this study, Four (4) classification algorithms were used, namely J48, Random Forest, Naïve Bayes, and REPTree.