An Intelligent Model To Predict Student's Performance Using Machine Learning Techniques

Abstract

The academic world of today is a complicated and highly competitive one. It is hard to evaluate student performance and provide high-quality education, as well as establish ways for assessing student achievement. In attempt to face the difficulties that students face while pursuing their education, educational institutions must establish student prevention strategies. Students' performance may be predicted using a Decision Tree (DT) model created in this study. The advancement of the learning environment is greatly aided by educational data mining, which contributes modern approaches, strategies, and applications. Students' learning environments may now be better understood via the use of machine learning and data mining approaches that use educational data. Students at trouble and students who drop out may be predicted using a variety of machine learning approaches, including K-Nearest Neighbor, Support Vector Machine, Logistic Regression (LR), and Naive Bayes (NB) algorithms. By using the DT technique to forecast student performance, this suggested model may be able to perform better.