Predicting College Students Dropout using EDM Techniques

Abstract

This study examines the factors affecting students' academic performance that contribute to the prediction of their failure and dropout using educational data mining techniques. This paper suggests the use of various classification techniques to identify the weak students who are likely to perform poorly in their academics. WEKA, an open source data mining tool was used to evaluate the attributes predicting student failure. The data set is comprised of 67 attributes of 150 students who have enrolled in B. Tech Degree Course registered for the academic year 2014-18 in a reputed college in Kerala affiliated to M.G University, Kerala, India. Various classification techniques like induction rules and decision tree have been applied to the data. The results of each of these approaches have been compared to select the one that achieves high accuracy.