Data Mining Techniques Used in Predicting Student Retention in Higher Education: A Survey

Predicting student retention is a crucial task for all stakeholders in higher education. This paper surveyed the Educational Data Mining (EDM) literature to explore the most recent methods used in building predictive models to predict student's retention, and to foresee the future trends in different context of higher education. We review a diversified set of approaches, models, data sets, tools, techniques, and performance measures. The approaches vary as the educational context varies where opportunities and challenges are associated with each approach. We also present a discussion and a foresight of future directions.