Training data selection for imbalanced cross-project defect prediction. (September 2021)

• Record Type: Journal Article
• Authors: Zheng, Shang; Gai, Jinjing; Yu, Hualong; Zou, Haitao; Gao, Shang
• Is Part Of: Computers & electrical engineering. Volume 94(2021)
• Publication Date: 2021-09
• Subjects: Cross-project software prediction -- Data selection -- Jensen-Shannon divergence -- Relative density; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107370
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Cross-project defect prediction with effective training data is considered. Jensen-Shannon divergence is applied to select the source project most similar to the target project. A grouped synthetic minority oversampling technique is used to solve the imbalanced problem. Results indicate that the proposed approach can improve the prediction performance. Abstract: Machine learning methods have been applied in software engineering to effectively predict software defects. Researchers proposed cross-project defect prediction (CPDP) for cases in which few or no data are available. CPDP uses the labeled data of a source project to construct a prediction model for the target project. However, the prediction performance remains inferior because the training data selection for the source project is ineffective. In this paper, the Jensen-Shannon divergence is first applied to automatically select the source project most similar to the target project. Subsequently, a grouped synthetic minority oversampling technique (SMOTE) is applied to improve the class imbalance of the projects. Finally, relative density estimation is performed to select the data for the source project. The experimental results demonstrate that the proposed method improves the prediction performance and exhibits high adaptability to different classifiers. Graphical abstract: Image, graphical abstract