I. INTRODUCTION
According to the Research Triangle Institute (RTI), software defects cost the U.S. economy billions of U.S. dollars annually, and more than a third of the costs associated with software defects could be avoided by improving software testing [1]. Software defect prediction can be modeled as a data mining problem by categorizing software unites as either fault prone (fp) or non-fault-prone (nfp) using historical data. Applying data mining and knowledge discovery (DMKD) in software reliability management has made remarkable progress [2]utilizing methods, algorithms, and techniques from many disciplines, including statistics, databases, machine learning, pattern recognition, artificial intelligence, data visualization, and optimization [3].