An Empirical Study on Fault Prediction using Token-Based Approach

Abstract

Since exhaustive testing is not possible, prediction of fault prone modules can be used for prioritizing the components of a software system. Various approaches have been proposed for the prediction of fault prone modules. Most of them uses module metrics as quality estimators. In this study, we proposed a tokenbased approach and combine the metric evaluated from our approach with the module metrics to further improve the prediction results. We conducted the experiment on an open source project for evaluating the approach. The proposed approach is further compared with the existing fault prone filtering technique. The results show that the proposed approach is an improvement over fault prone filtering technique.