TRAINING NEURAL NETWORKS TO PREDICT STUDENT ACADEMIC PERFORMANCE: A COMPARISON OF CUCKOO SEARCH AND GRAVITATIONAL SEARCH ALGORITHMS

Abstract

The accurate prediction of students' academic performance is of importance to institutions as it provides valuable information for decision making in the admission process and enhances educational services by allocating customized assistance according to the predicted performance. The purpose of this study is to investigate the prediction ability of neural networks trained by two recent heuristic algorithms inspired by the behaviors of natural phenomena, namely, the cuckoo search and gravitational search algorithms. We used previous exam results and other factors, such as the location of the student's high school and the student's gender, as input variables, and predicted the student's expected performance. The cuckoo search and gravitational search algorithms were utilized to train the feed-forward neural network for prediction. These algorithms optimized the weights between layers and biases of the neuron network. The simulation results of the two algorithms were then discussed and analyzed. It was found that the neural network trained by the cuckoo search could be used in the prediction of students' academic performance. It is expected that this work may be used to support student admission procedures and strengthen the service system in educational institutions.