Analyzing Undergraduate Students’ Performance in Various Perspectives using Data Mining Approach

Abstract

The data mining provides better insight rather than the predefined queries or reports for quality enhancement and improvement of an academic program to extract hidden knowledge in students’ performance in various courses. This paper presents data mining approach applied to discover students’ performance patterns in two different perspectives (a) supervised and unsupervised assessment instruments and (b) discover students’ performance patterns in mathematics, English, and programming courses in an engineering degree program. The interesting patterns emerging from both analytic studies offer helpful and constructive suggestions for the improvement and revision of assessment methodologies, restructuring the curriculum, and modifying the prerequisites requirements of various courses.

Keywords: Association Rules, Supervised and Unsupervised Assessment, Educational Data Mining