Neural Network and Linear Regression methods for prediction of students' academic achievement

Abstract

Prediction of students' academic performance is very crucial to any university management to reduce the rate of attrition among students upon graduation. This paper describes a Neural Network (NN) Prediction model that is used to predict the academic performance of students. The outcomes of this model are then compared to results using Linear Regression (LR). This paper presents a comparison study between the effects of fundamental subjects and English courses on the overall final performance of students. The study was carried out at Universiti Teknologi Mara (UiTM) Malaysia. Grade Points (GP) of students' fundamental subjects results were used as independent variables or input predictor variables while CGPA in the final semester that is at semester eight is used as the output or the dependent variable. Performances of the models were measured using the coefficient of Correlation R and that of Mean Square Error (MSE). The outcomes of the study from both models indicate a strong correlation between fundamental results for core subjects with the final CGPA. English courses had little effects on the final CGPA.