A Comparative Analysis of Techniques for Predicting Academic Performance

Abstract

The main objective of the admission system is to determine candidates who would likely do well in the university. The quality of candidates admitted into any higher institution affects the level of research and training within the institution, and by extension, has an overall effect on the development of the country itself, as these candidates eventually become key players in the affairs of the country in all sectors of the economy. This article compares the accuracy of various data mining techniques, namely: decision trees, logistic regression, neural network, naive bayes, association rules and clustering for predicting the academic performance of the first semester for the undergraduate engineering students at the Modern Academy for Engineering (MAE) by using the high school grade as the only input, and proposes a method that allows best prediction results from different prediction algorithms to be selected. A set of data has been tried to proof the correctness of the proposed method. According to the obtained results, the data-mining tools were able to achieve levels of accuracy for predicting student performance. The results showed that decision trees, clustering, and naive bayes score was a little more than the other three for the sets {pass, fail} and {excellent, very good, good, pass, fail, very bad, absent} while association rules, came out the last with the least score for both sets. The results of these case studies give insight into techniques for accurately predicting student performance and compare the accuracy of data mining algorithms.