To identify the improvement pattern of self-financing arts and science college student’s academic performance using classification algorithms

Abstract

The aim of this research work is to identify the improvement pattern of academic performance of final year students of self-financing arts and science colleges. The data was collected from the students of nine Arts and Science Colleges. The data contains demographic, socio-economic, residence and college location, subjects, infrastructural facilities, faculty concern and self-motivation attributes. The classification algorithms like Naïve Bayes, Decision tree and CBPANN are applied on the student’s data. The outcome of the research can be used to improve the academic performance students studying in self-financing arts and science colleges located in educationally backward areas. The experiment results shows that the accuracy value for Naïve Bayes algorithm is 92.63%, accuracy value for Decision Tree algorithm is 96.41% and accuracy value for CBPANN algorithm is 99.49%.