Educational Data Mining for Student Performance Prediction

Main Article Content

Linqiang Tang
Chen Sian

Abstract

The topic of Educational Data Mining (EDM) has gained significant traction in improving the quality of education by identifying patterns and insights through the analysis of data gathered from diverse educational settings. In order to discover important elements that affect educational achievement and to give educators and policymakers with useful insights, this study investigates the use of machine learning techniques in predicting student performance. We use a variety of machine learning methods, such as decision trees, support vector machines, and neural networks, to create predictive models by utilizing past educational information, demographics, and behavioral tendencies. The study assesses these models’ efficacy and accuracy while also emphasizing how important choosing features and data preparation are to enhancing prediction results. Our results show that applying machine learning approaches can greatly improve the prediction of pupil achievement, which in turn allows for more focused interventions and individualized learning plans. This study highlights the possibilities of machine learning in promoting a data-driven method to educational improvement and adds to the expanding body of knowledge in EDM.

Article Details

Section
Special Issue - Cognitive Computing for Distributed Data Processing and Decision-Making in Large-Scale Environments