DSpace Repository

Model analytics for defect prediction based on design-level metrics and sampling techniques

Show simple item record

dc.contributor.author Kaya, Aydın
dc.contributor.author Keçeli, Ali Seydi
dc.contributor.author Çatal, Çağatay
dc.contributor.author Tekinerdoğan, Bedir
dc.date.accessioned 2021-06-10T11:33:45Z
dc.date.available 2021-06-10T11:33:45Z
dc.date.issued 2020
dc.identifier.citation Kaya, Aydın...et al (2020). "Model analytics for defect prediction based on design-level metris and sampling techniques", Model Management and Analytics for Large Scale Systems, Academic Press, 2020, pp. 125-139. tr_TR
dc.identifier.isbn 9780128166499
dc.identifier.uri http://hdl.handle.net/20.500.12416/4759
dc.description.abstract Predicting software defects in the early stages of the software development life cycle, such as the design and requirement analysis phase, provides significant economic advantages for software companies. Model analytics for defect prediction lets quality assurance groups build prediction models earlier and predict the defect-prone components before the testing phase for in-depth testing. In this study, we demonstrate that Machine Learning-based defect prediction models using design-level metrics in conjunction with data sampling techniques are effective in finding software defects. We show that design-level attributes have a strong correlation with the probability of defects and the SMOTE data sampling approach improves the performance of prediction models. When design-level metrics are applied, the Adaboost ensemble method provides the best performance to detect the minority class samples. tr_TR
dc.language.iso eng tr_TR
dc.publisher Academic Press tr_TR
dc.relation.isversionof 10.1016/B978-0-12-816649-9.00015-6 tr_TR
dc.rights info:eu-repo/semantics/closedAccess tr_TR
dc.subject Defect Prediction tr_TR
dc.subject Design-Level Metrics tr_TR
dc.subject Sampling Techniques tr_TR
dc.subject Software Defects tr_TR
dc.subject Model Analytics tr_TR
dc.title Model analytics for defect prediction based on design-level metrics and sampling techniques tr_TR
dc.type bookPart tr_TR
dc.relation.journal Model Management and Analytics for Large Scale Systems tr_TR
dc.contributor.authorID 3530 tr_TR
dc.identifier.startpage 125 tr_TR
dc.identifier.endpage 139 tr_TR
dc.contributor.department Çankaya Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü tr_TR


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record