Fault prediction model for software using soft computing techniques

Faulty modules of any software can be problematic in terms of accuracy, hence may encounter more costly redevelopment efforts in later phases. These problems could be addressed by incorporating the ability of accurate prediction of fault prone modules in the development process. Such ability of the software enables developers to reduce the faults in the whole life cycle of software development, at the same time it benefits automation process, and reduces the overall cost and efforts of the software maintenance. In this paper, we propose to design fault prediction model by using a set of code and design metrics; applying various machine learning (ML) classifiers; also used transformation techniques for feature reduction and dealing class imbalance data to improve fault prediction model. The data sets were obtained from publicly available PROMISE repositories. The results of the study revealed that there was no significant impact on the ability to accurately predict the fault-proneness of modules by applying PCA in reducing the dimensions; the results were improved after balancing data by SMOTE, Resample techniques, and by applying PCA with Resample in combination. It has also been seen that Random Forest, Random Tree, Logistic Regression, and Kstar machine learning classifiers have relatively better consistency in prediction accuracy as compared to other techniques.