Educational data mining for prediction and classification of engineering students achievement

Abstract

This paper highlights the importance of using student data to drive improvement in education planning. It then presents techniques of how to obtain knowledge from databases such as large arrays of student data from academic Institution databases. Further, it describes the development of a tool that will enable faculty members to identify, predict and classify students based on academic performance measured using Cumulative Grade point average (CGPA) grades. The need for prediction of a student's performance is to enable the university to intervene and provide assistance to low achievers as early as possible. Included in the paper is a brief overview of the most commonly used classifiers techniques in educational data mining and an outline of the use of Neuro-Fuzzy classification in a case study research to predict and classify students' academic achievement in an Electrical Engineering faculty of a Malaysian public university.