On the Automation of Software Fault Prediction

This paper discusses the issues involved in building a practical automated tool to predict the incidence of software faults in future releases of a large software system. The possibility of creating such a tool is based on the authors' experience in analyzing the fault history of several large industrial software projects, and constructing statistical models that are capable of accurately predicting the most fault-prone software entities in an industrial environment. The emphasis of this paper is on the issues involved in the tool design and construction and an assessment of the extent to which the entire process can be automated so that it can be widely deployed and used by practitioners who do not necessarily have any particular statistical or modeling expertise