DROPOUT STUDENT PREDICTION USING NAÏVE BAYS CLASSIFIER

Abstract

The objectives of this research work is to identify relevant attribute from socio-demographic, academic and institutional data of first year students from undergraduate at the University and design a prototype machine learning tool which can routinely distinguish whether the student persist their revise or drop their learning using classification technique based on decision tree. For powerful decision making tool different parameter are need to be considered such as socio-demographic data, parental attitude and institutional factors. The generated knowledge will be quite useful for tutor and management of university to develop policies and strategies related to increase the enrolment rate in University and to take precautionary and consultative procedures and thereby diminish student dropout. It can also use to find the reasons and relevant factors that affect the dropout students.