ABSTRACT

Predicting the performance of a student is a great concern to the higher education managements, where several factors affect the performance. The scope of this paper is to investigate the accuracy of data mining techniques in such an environment. The first step of the study is to gather student’s data on technical, analytical, communicational and problem solving abilities. We collected records of 200 Post graduate students of computer science course, from a private Educational Institution conducting various Under Graduate and Post Graduate courses. The second step is to clean the data and choose the relevant attributes. Attributes were classified into two groups “Demographic Attributes” and “Performance Attributes”. In the third step, Decision tree and Naive bayes algorithms were constructed and their performances were evaluated. The study revealed that the Decision tree algorithm is more accurate than the Naïve bayes algorithm. This work will help the institute to accurately predict the performance of the students.