A standard process for data mining based software debugging

Abstract

The importance of software is increasing in scientific research and our daily life. Meanwhile, the cost and consequences of software failure caused by software bugs become more and more serious. This paper proposes a standard process for data mining based software debugging. The proposed process provides guidelines for software testing engineers and researchers on how to apply data mining techniques and software testing theory on real life software testing projects. This paper defined the DM based software debugging project as a five-step process: (1) Establish the software testing project; (2) Data collecting, cleaning and transformation; (3) Select, train and verify the data mining models; (4) Classify, locate and describe the software bug found in previous steps; and (5) deploy the knowledge gained into real life software testing project. © 2008 IEEE.