Educational Data Mining: A Comprehensive Review and Future Challenges

Abstract

Students are the major clients of many institutions, and they've come to realize that they're in the service industry. Before designing a performance-enhancement program, a student's existing status must be evaluated. Higher education officials place a strong focus on accurately predicting a student's performance. This study tries to reveal the many factors that influence a student's choice to join a certain college or institution. Students who are able to forecast their own performance early on are better able to take action to enhance their results. In order to achieve a high level of education, several forecasts of student performance have been devised. However, these predictions have been shown to be inadequate. EDM uses a variety of elements, including social, behavioral, cognitive, and motivational, to predict student behavior. Many domain models have previously been improved by using optimal learning and instructional sequences. This article examines a variety of educational data mining strategies in great detail. Data mining in education also faces a number of concerns and obstacles, which are explored in this article.