A novel academic performance estimation model using two stage feature selection

Abstract

Educational data mining has gained tremendous interest from researchers across the globe. Using data mining techniques in the field of education several significant findings have been made. Accurate academic performance estimation has been a challenging task due to the variety of students’ attributes involved. In this study we have developed a novel framework to estimate the academic performance of students. Our proposed model outperformed existing models of students’ academic performance determination and gives a new direction to academic performance estimation. The proposed model can help not only to reduce the number of academic failures but also help to comprehend the factors contributing to a students’ academic performance (poor, average or outstanding). Some of the techniques used were conversion of categorical attributes into dummy variables, instance segregation, classification using an optimised and improved differential evolutionary algorithm.