Keywordsīrun, Y., Ernst, M.D.: Finding Latent Code Errors via Machine Learning over Program Executions. We find that history based and change level hunk metrics are better predictors of bugs than code level hunk metrics. Our classifier can classify individual hunks as buggy or bug-free with 86 % accuracy, 83 % buggy hunk precision and 77% buggy hunk recall. Hunk metrics are used to train the classifier and each hunk metric is evaluated for its bug prediction capabilities.
We build bug prediction models using random forests, which is an efficient machine learning classifier. We present a technique for bug prediction that works at smallest units of code change called hunks.
In this paper we empirically evaluate the use of hunk metrics as predictor of bugs. These metrics have been used to build bug predictor models to help developers maintain the quality of software. Software process and product metrics are good indicators of software complexity. Reducing the number of bugs is a crucial issue during software development and maintenance.
0 kommentar(er)
