A neuro-fuzzy classification approach to the assessment of student performance

This paper reports on the design and development of a neuro-fuzzy classification technique for predicting the student performance in a college of engineering. The main function of the neuro-fuzzy classifier is to investigate the rules that describe the students performance and classify them into three different groups based on their expected performance. This work could support the student admittance procedure by evaluating and predicting student performance before acceptance to the college as well as assessing the suitability of the entry exams. The experiment demonstrated that some of the entry exams gave a good indication of the student level while other exams did not predict the correct student level.