Metrics selection for fault-proneness prediction of software modules

It would be valuable to use metrics to identify the fault-proneness of software modules. It is important to select the most appropriate particular metric subset for fault-proneness prediction. We proposed an approach of metrics selection, which firstly utilized the correlation analysis to eliminate the high the correlation metrics and then ranked the remaining metrics based on the gray relational analysis. Three classifiers, that were logistic regression model, NaiveBayes, and J48, were utilized to empirically investigate the usefulness of selected metrics. Our results, based on a public domain NASA data set, indicate that 1) proposed method for metrics selection is effective, and 2) using 3-4 metrics gets the balanced performance for fault-proneness prediction of software modules.