International Association of Engineers
Empirical validation of software metrics to predict quality using machine learning methods is important to ensure their practical relevance in the software organizations. In this paper, the authors build a Support Vector Machine (SVM) model to find the relationship between object-oriented metrics given by the researchers and fault proneness. The proposed model is empirically evaluated using public domain KC1 NASA data set. The performance of the SVM method was evaluated by Receiver Operating Characteristic (ROC) analysis.