Connecting Software Metrics across Versions to Predict Defects
This work addresses software practitioners' need for more accurate defect prediction to allocate testing resources efficiently, though it is incremental as it builds on existing metrics and RNN techniques.
The paper tackled the problem of software defect prediction by proposing the use of Historical Version Sequence of Metrics (HVSM) to capture module changes over project evolution, and found that an RNN model using HVSM significantly outperformed baseline models in effort-aware ranking effectiveness in most cases.
Accurate software defect prediction could help software practitioners allocate test resources to defect-prone modules effectively and efficiently. In the last decades, much effort has been devoted to build accurate defect prediction models, including developing quality defect predictors and modeling techniques. However, current widely used defect predictors such as code metrics and process metrics could not well describe how software modules change over the project evolution, which we believe is important for defect prediction. In order to deal with this problem, in this paper, we propose to use the Historical Version Sequence of Metrics (HVSM) in continuous software versions as defect predictors. Furthermore, we leverage Recurrent Neural Network (RNN), a popular modeling technique, to take HVSM as the input to build software prediction models. The experimental results show that, in most cases, the proposed HVSM-based RNN model has a significantly better effort-aware ranking effectiveness than the commonly used baseline models.