Analyzing the effect of bagged ensemble approach for software fault prediction in class level and package level metrics

Abstract

Faults in a module tend to cause failure of the software product. These defective modules in the software pose considerable risk by increasing the developing cost and decreasing the customer satisfaction. Hence in a software development life cycle it is very important to predict the faulty modules in the software product. Prediction of the defective modules should be done as early as possible so as to improve software developers' ability to identify the defect-prone modules and focus quality assurance activities such as testing and inspections on those defective modules. For quality assurance activity, it is important to concentrate on the software metrics. Software metrics play a vital role in measuring the quality of software. Many researchers focused on classification algorithm for predicting the software defect. On the other hand, classifiers ensemble can effectively improve classification performance when compared with a single classifier. This paper mainly addresses using ensemble approach of Support Vector Machine (SVM) for fault prediction. Ensemble classifier was examined for Eclipse Package level dataset and NASA KC1 dataset. We showed that proposed ensemble of Support Vector Machine is superior to individual approach for software fault prediction in terms of classification rate through Root Mean Square Error Rate (RMSE), AUC-ROC, ROC curves.