Abstract—Prediction of fault-prone modules provides one way to support software quality engineering through improved scheduling

Prediction of fault-prone modules provides one way to support software quality engineering through improved scheduling and project control. There are many metrics and techniques available to investigate the accuracy of fault prone classes which may help software organizations for planning and performing testing activities. Bayes algorithms are being successfully applied for solving both classification and regression problems. It is therefore important to investigate the capabilities of Bayes Network Classification algorithm in predicting software quality. In order to perform the analysis we validate the performance of the Bayes Network based Algorithm using open source software JEdit. In this paper, we investigate the capability of a Bayes Network Algorithm in predicting faulty classes. We investigate the accuracy of the fault proneness predictions using object oriented design metrics suite. By using Bayes Network Algorithm technique on fault prone classes may enable the software organizations, for planning and performing testing by focusing on accuracy of fault prone classes. This may result in significant improvement in software quality. Keywords— A bayes network classification approach, Software fault, Object Oriented Metrics.