USING ENSEMBLE DATA MINING APPROACHES TO PREDICTING STUDENT ACADEMIC PERFORMANCE

Providing an effective learning environment that fosters student academic success is fundamentally important for all institutions of higher education. This paper investigates and applies several ensemble data mining approaches to identifying significant factors that are associated with student success and to accurately predicting student academic performance for classes from freshman through senior. While the paper focuses on the performance prediction through student data collected from a US college, the methodology developed from this work will be applicable to similar or different educational institutions. Furthermore, prediction of student academic success is consistently related to several key areas of higher education planning and administration that include enrollment management, student retention, scholarship and financial aid supervision, and graduation time projection. Finally, the paper demonstrates that ensemble data mining methods can produce superior or competitive prediction models in comparison with several other well-known traditional approaches such as decision trees.