Mining Software Metrics from Jazz
This work addresses the problem of predicting software build outcomes for developers, but it is incremental as it applies existing methods to a new dataset.
The authors extracted source code metrics from the Jazz repository and applied data mining to identify which metrics best predict build success or failure, finding that only a small number of metrics were significant for this prediction.
In this paper, we describe the extraction of source code metrics from the Jazz repository and the application of data mining techniques to identify the most useful of those metrics for predicting the success or failure of an attempt to construct a working instance of the software product. We present results from a systematic study using the J48 classification method. The results indicate that only a relatively small number of the available software metrics that we considered have any significance for predicting the outcome of a build. These significant metrics are discussed and implication of the results discussed, particularly the relative difficulty of being able to predict failed build attempts.