An intelligent approach to educational data: Performance comparison of the multilayer perceptron and the radial basis function artificial neural networks

Abstract

The objective of this study is twofold: (1) to investigate the factors that affect the success of university students by employing two artificial neural network methods (i.e., multilayer perceptron [MLP] and radial basis function [RBF]); and (2) to compare the effects of these methods on educational data in terms of predictive ability. The participants’ transcript scores were used as the target variables and the two methods were employed to test the predictors that affected these variables. The results show that the multilayer perceptron artificial neural network outperformed the radial basis artificial neural network in terms of predictive ability. Although the findings suggest that research in quantitative educational science should be conducted by using the former artificial neural network method, additional supporting evidence needs to be collected in related studies. © 2015 EDAM.