Predicting failures with developer networks and social network analysis

TLDR

Software failures are costly, and while predictive models have been successful, most ignore the key role of developers. The study aims to determine whether the structure of developer collaboration can explain product reliability. The authors built developer networks from code‑churn data, trained failure‑prediction models on two Nortel releases, and validated them on a third release. The model identified 58 % of failures in the top 20 % of files, close to the 61 % optimal, confirming a strong link between developer network metrics and failures.

Abstract

Software fails and fixing it is expensive. Research in failure prediction has been highly successful at modeling software failures. Few models, however, consider the key cause of failures in software: people. Understanding the structure of developer collaboration could explain a lot about the reliability of the final product. We examine this collaboration structure with the developer network derived from code churn information that can predict failures at the file level. We conducted a case study involving a mature Nortel networking product of over three million lines of code. Failure prediction models were developed using test and post-release failure data from two releases, then validated against a subsequent release. One model's prioritization revealed 58% of the failures in 20% of the files compared with the optimal prioritization that would have found 61% in 20% of the files, indicating that a significant correlation exists between file-based developer network metrics and failures.