Predicting students’ academic achievement: Comparison between logistic regression, artificial neural network, and Neuro-fuzzy

Abstract

Predicting students’ academic performance is critical for educational institutions because strategic programs can be planned in improving or maintaining students’ performance during their period of studies in the institutions. The academic performance in this study is measured by their cumulative grade point average (CGPA) upon graduating. In this study, the students’ demographic profile and the CGPA for the first semester of the undergraduate studies are used as the predictor variable for the students’ academic performance in the under-graduate degree program. Three predictive models have been developed, namely, logistic regression, artificial neural network (ANN) and Neuro-fuzzy. Performances of all the models were measured using root mean squared error (RMSE). The experiments indicate that Neuro-fuzzy model is better than logistic regression and ANN.