A Comparison of Classification Algorithms for Software Defect Prediction

With the increased growth of developed software in daily life, there is an urgent need to predict software defects. The aim of this study is to compare the performance of three classification algorithms for software defect prediction. The algorithms are random forest (RF), Naïve Bayes (NB), and Decision Tree (DT). Thus, the primary purpose of using these algorithms is to find their effects on the hybrid binary whale optimization algorithm with a taper-shaped transfer function for dimension reduction in software defect prediction. Thus, three models are proposed for software defect prediction. Six datasets have been used to evaluate the performance of the proposed model in terms of error rate, selected features, and prediction accuracy. The experimental results demonstrated that the Naïve Bayes (NB) algorithm provides the best accuracy with minimum error and a number of selected features compared to the random forest (RF) and Decision Tree (DT) algorithms for solving software defect prediction.