Enhancement of E-Learning Student’s Performance Based on Ensemble Techniques

Educational institutions have dramatically increased in recent years, producing many graduates and postgraduates each year. One of the critical concerns decision-makers is student performance. data mining techniques are beneficial to explore uncovered itself, creating a pattern analyze In this study, we investigate E-learning that has significantly era COVID-19. Thus, study aims predict performance using information gathered from online systems. Evaluating through model proposed will help make informed suitable decisions for their institution. The includes three traditional methods, decision tree, Naive Bays, random forest, which further enhanced by use ensemble techniques: bagging, boosting, voting. results demonstrated improved accuracy 0.75 0.77 when used DT method with boosting. Furthermore, precision recall both 0.76 0.78.