Empirical evaluation of mixed-project defect prediction models

Burak Turhan, Ayse Tosun, Ayşe Bener

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

17 Citations (Scopus)

Abstract

Defect prediction research mostly focus on optimizing the performance of models that are constructed for isolated projects. On the other hand, recent studies try to utilize data across projects for building defect prediction models. We combine both approaches and investigate the effects of using mixed (i.e. within and cross) project data on defect prediction performance, which has not been addressed in previous studies. We conduct experiments to analyze models learned from mixed project data using ten proprietary projects from two different organizations. We observe that code metric based mixed project models yield only minor improvements in the prediction performance for a limited number of cases that are difficult to characterize. Based on existing studies and our results, we conclude that using cross project data for defect prediction is still an open challenge that should only be considered in environments where there is no local data collection activity, and using data from other projects in addition to a project's own data does not pay off in terms of performance.

Original languageEnglish
Title of host publicationProceedings - 37th EUROMICRO Conference on Software Engineering and Advanced Applications, SEAA 2011
Pages396-403
Number of pages8
DOIs
Publication statusPublished - 12 Dec 2011
Externally publishedYes
Event37th EUROMICRO Conference on Software Engineering and Advanced Applications, SEAA 2011 - Oulu, Finland
Duration: 30 Aug 20112 Sep 2011

Conference

Conference37th EUROMICRO Conference on Software Engineering and Advanced Applications, SEAA 2011
CountryFinland
CityOulu
Period30/08/112/09/11

Keywords

  • cross project
  • defect prediction
  • mixed project
  • product metrics
  • within project

Cite this

Turhan, B., Tosun, A., & Bener, A. (2011). Empirical evaluation of mixed-project defect prediction models. In Proceedings - 37th EUROMICRO Conference on Software Engineering and Advanced Applications, SEAA 2011 (pp. 396-403). [6068375] https://doi.org/10.1109/SEAA.2011.59