Change Bursts as Defect Predictors – ISSRE 2010

by Nachiappan Nagappan, Andreas Zeller, Thomas Zimmermann, Kim Herzig, Brendan Murphy

In software development, every change induces a risk. What happens if code changes again and again in some period of time? In an empirical study on Windows Vista, we found that the features of such change bursts have the highest predictive power for defect-prone components. With precision and recall values well above 90%, change bursts significantly improve upon earlier predictors such as complexity metrics, code churn, or organizational structure. As they only rely on version history and a controlled change process, change bursts are straight-forward to detect and deploy.

Download as PDF.


Nachiappan Nagappan, Andreas Zeller, Thomas Zimmermann, Kim Herzig, Brendan Murphy. Change Bursts as Defect Predictors. In Proceedings of the 21st IEEE International Symposium on Software Reliability Engineering (ISSRE 2010), San Jose, California, USA, November 2010.

BibTeX Entry

    title = "Change Bursts as Defect Predictors",
    author = "Nachiappan Nagappan and Andreas Zeller and Thomas Zimmermann and Kim Herzig and Brendan Murphy",
    year = "2010",
    month = "November",
    booktitle = "Proceedings of the 21st IEEE International Symposium on Software Reliability Engineering",
    location = "San Jose, California, USA",