Abstract | ||
---|---|---|
Many empirical studies have shown that defect prediction models built on product metrics can be used to assess the quality of software modules. So far, most methods proposed in this direction predict defects by class or file. In this paper, we propose a novel software defect prediction method based on functional clusters of programs to improve the performance, especially the effort-aware performance, of defect prediction. In the method, we use proper-grained and problem-oriented program clusters as the basic units of defect prediction. To evaluate the effectiveness of the method, we conducted an experimental study on Eclipse 3.0. We found that, comparing with class-based models, cluster-based prediction models can significantly improve the recall (from 31.6% to 99.2%) and precision (from 73.8% to 91.6%) of defect prediction. According to the effort-aware evaluation, the effort needed to review code to find half of the total defects can be reduced by 6% if using cluster-based prediction models. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/WCRE.2011.37 | WCRE |
Keywords | Field | DocType |
defect prediction,assessing software quality,cluster-based prediction model,total defect,program clustering,software module,effort-aware evaluation,effort-aware performance,basic unit,novel software defect prediction,class-based model,defect prediction model,software metrics,semantics,measurement,predictive models,linear regression,logistics,software quality | Data mining,Computer science,Software bug,Software,Predictive modelling,Software metric,Cluster analysis,Software quality,Product metric,Linear regression | Conference |
Citations | PageRank | References |
6 | 0.39 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xi Tan | 1 | 73 | 14.27 |
Xin Peng | 2 | 599 | 67.59 |
Sen Pan | 3 | 6 | 0.73 |
Wenyun Zhao | 4 | 526 | 54.45 |