Date Added: Jun 2012
Defective modules pose considerable risk by decreasing customer satisfaction and by increasing the development and maintenance costs. Therefore, in software development life cycle, it is essential to predict defective modules as early as possible so as to improve software developers' ability to identify the defect-prone modules and focus quality assurance activities such as testing and inspections on those modules. Software metrics play an important role in measuring the quality of software. It is desirable to predict the quality of software as early as possible, and hence metrics have to be collected early as well. This paper is focused on the high-performance fault predictors based on machine learning algorithms.