Improving software fault-prediction for imbalanced data

• Published in: 2012 International Conference on Innovations in Information Technology pp. 54 - 59
• Main Author: Shatnawi, R.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2012
• Subjects: CK metrics; data mining; Data models; fault-proneness; imbalanced data; Measurement; Object oriented modeling; Predictive models; ROC curve; Software engineering; Software quality
• ISBN: 9781467311007; 1467311006
• DOI: 10.1109/INNOVATIONS.2012.6207774

Fault-proneness has been studied extensively as a quality factor. The prediction of fault-proneness of software modules can help software engineers to plan evolutions of the system. This plan can be compromised in case prediction models are biased or do not have high prediction performance. One major issue that can impact the prediction performance is the fault distributions such as the data imbalance, i.e., the majority of modules are faultless whereas the minority of modules is only faulty. In this paper, we propose to use the fault content (i.e., the number of faults in a module) to oversample the minority. We applied this technique on a large object-oriented system - Eclipse. The proposed oversampling is tested on three classifiers. The results have shown a better prediction performance than other traditional oversampling techniques. The oversampling technique is more convenient than other sampling techniques because it's guided by information provided from the software history.