Comparing the Effectiveness of Machine Learning Algorithms for Defect Prediction

Software repositories with defect logs are main resource for defect prediction. In recent years, researchers have used the vast amount of data that is contained by software repositories to predict the location of defect in the code that caused problem. In this paper machine learning approach is used for predicting the modules with defect for embedded data set. Public datasets from the promise repository have been explored for identifying software defects using machine learning methods. The repository contains software metric data and error data at the function/method level. The aim of the paper is to classify embedded data set using J48, OneR and Naïve Bayes machine learning algorithms to construct a model that predicts potentially defected modules within a given set of software modules with respect to their metric data and study the performance of these machine learning algorithms. The result is compared on the basis of confusion matrices. The study showed that J48 and OneR performed better than Naive Bayes.