An empirical study on the effectiveness of data resampling approaches for cross-project software defect prediction

Simple item page
dc.citation.issue2
dc.citation.volume16
dc.contributor.authorBennin KE
dc.contributor.authorTahir A
dc.contributor.authorMacDonell SG
dc.contributor.authorBörstler J
dc.date.accessioned2023-11-23T01:28:26Z
dc.date.accessioned2024-07-25T06:45:20Z
dc.date.available2021-11-28
dc.date.available2023-11-23T01:28:26Z
dc.date.available2024-07-25T06:45:20Z
dc.date.issued2022-04
dc.description.abstractCross-project defect prediction (CPDP), where data from different software projects are used to predict defects, has been proposed as a way to provide data for software projects that lack historical data. Evaluations of CPDP models using the Nearest Neighbour (NN) Filter approach have shown promising results in recent studies. A key challenge with defect-prediction datasets is class imbalance, that is, highly skewed datasets where non-buggy modules dominate the buggy modules. In the past, data resampling approaches have been applied to within-projects defect prediction models to help alleviate the negative effects of class imbalance in the datasets. To address the class imbalance issue in CPDP, the authors assess the impact of data resampling approaches on CPDP models after the NN Filter is applied. The impact on prediction performance of five oversampling approaches (MAHAKIL, SMOTE, Borderline-SMOTE, Random Oversampling and ADASYN) and three undersampling approaches (Random Undersampling, Tomek Links and One-sided selection) is investigated and results are compared to approaches without data resampling. The authors examined six defect prediction models on 34 datasets extracted from the PROMISE repository. The authors' results show that there is a significant positive effect of data resampling on CPDP performance, suggesting that software quality teams and researchers should consider applying data resampling approaches for improved recall (pd) and g-measure prediction performance. However, if the goal is to improve precision and reduce false alarm (pf) then data resampling approaches should be avoided.
dc.description.confidentialfalse
dc.edition.editionApril 2022
dc.format.pagination185-199
dc.identifier.author-urlhttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000723085500001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=c5bb3b2499afac691c2e3c1a83ef6fef
dc.identifier.citationBennin KE, Tahir A, MacDonell SG, Börstler J. (2022). An empirical study on the effectiveness of data resampling approaches for cross-project software defect prediction. IET Software. 16. 2. (pp. 185-199).
dc.identifier.doi10.1049/sfw2.12052
dc.identifier.eissn1751-8814
dc.identifier.elements-typejournal-article
dc.identifier.issn1751-8806
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/70798
dc.languageEnglish
dc.publisherJohn Wiley and Sons Ltd on behalf of The Institution of Engineering and Technolog
dc.publisher.urihttps://ietresearch.onlinelibrary.wiley.com/doi/10.1049/sfw2.12052
dc.relation.isPartOfIET Software
dc.rights(c) 2021 The Author/s
dc.rightsCC BY-NC-ND 4.0
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.en
dc.subjectclass imbalance
dc.subjectdefect prediction
dc.subjectsoftware metrics
dc.subjectsoftware quality
dc.titleAn empirical study on the effectiveness of data resampling approaches for cross-project software defect prediction
dc.typeJournal article
pubs.elements-id451776
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Published version
Size:
1.31 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Journal Articles