Quality Assessment Based on Attribute Series of Software Evolution

Defect density and defect prediction are essential for efficient resource allocation in software evolution. In an empirical study we applied data mining techniques for value series based on evolution attributes such as number of authors, commit messages, lines of code, bug fix count, etc. Daily data points of these evolution attributes were captured over a period of two months to predict the defects in the subsequent two months in a project. For that, we developed models utilizing genetic programming and linear regression to accurately predict software defects. In our study, we investigated the data of three independent projects, two open source and one commercial software system. The results show that by utilizing series of these attributes we obtain models with high correlation coefficients (between 0.716 and 0.946). Further, we argue that prediction models based on series of a single variable are sometimes superior to the model including all attributes: in contrast to other studies that resulted in size or complexity measures as predictors, we have identified the number of authors and the number of commit messages to versioning systems as excellent predictors of defect densities.