Empirical validation of object-oriented metrics for predicting fault proneness at different severity levels using support vector machines

Empirical validation of software metrics to predict quality using machine learning methods is important to ensure their practical relevance in the software organizations. It would also be interesting to know the relationship between object-oriented metrics and fault proneness at different severity levels. In this paper, we build a Support vector machine (SVM) model to find the relationship between object-oriented metrics given by Chidamber and Kemerer and fault proneness, at different severity levels. The proposed models at different severity levels are empirically evaluated using public domain NASA data set. The performance of the SVM method was evaluated by receiver operating characteristic (ROC) analysis. Based on these results, it is reasonable to claim that such models could help for planning and performing testing by focusing resources on fault-prone parts of the design and code. The performance of the model predicted using high severity faults is low as compared to performance of the model predicted with respect to medium and low severity faults. Thus, the study shows that SVM method may also be used in constructing software quality models. However, similar types of studies are required to be carried out in order to establish the acceptability of the model.