On the time-based conclusion stability of cross-project defect prediction models

Abdul Ali Bangash, Hareem Sahar, Abram Hindle, Karim Ali

Research output: Contribution to journalArticlepeer-review


Researchers in empirical software engineering often make claims based on observable data such as defect reports. Unfortunately, in many cases, these claims are generalized beyond the data sets that have been evaluated. Will the researcher’s conclusions hold a year from now for the same software projects? Perhaps not. Recent studies show that in the area of Software Analytics, conclusions over different data sets are usually inconsistent. In this article, we empirically investigate whether conclusions in the area of cross-project defect prediction truly exhibit stability throughout time or not. Our investigation applies a time-aware evaluation approach where models are trained only on the past, and evaluations are executed only on the future. Through this time-aware evaluation, we show that depending on which time period we evaluate defect predictors, their performance, in terms of F-Score, the area under the curve (AUC), and Mathews Correlation Coefficient (MCC), varies and their results are not consistent. The next release of a product, which is significantly different from its prior release, may drastically change defect prediction performance. Therefore, without knowing about the conclusion stability, empirical software engineering researchers should limit their claims of performance within the contexts of evaluation, because broad claims about defect prediction performance might be contradicted by the next upcoming release of a product under analysis.

Original languageEnglish (US)
Pages (from-to)5047-5083
Number of pages37
JournalEmpirical Software Engineering
Issue number6
StatePublished - Nov 1 2020


  • Conclusion stability
  • Defect prediction
  • Time-aware evaluation

ASJC Scopus subject areas

  • Software


Dive into the research topics of 'On the time-based conclusion stability of cross-project defect prediction models'. Together they form a unique fingerprint.

Cite this