An approach for software defect prediction by combined soft computing

Abstract

Nowadays, software project success is the key challenge. Prediction of software defects is main focus for the engineering community. A recent study in literature shows that data mining techniques are wildly used to predict software projects success. Many software development companies maintain their own software repositories, it is helpful for the prediction of software defects. There is dire need to reduce the gap between the software engineering and data mining community to increase the rate of software projects success. Although software defect prediction using classification/clustering algorithms has been encouraged by many researchers. However the lack of performance due to single classifier/clustering algorithms used for defect prediction. This paper provides software defect prediction using integrated approaches are advocated, instead of single classifier/clustering. The experimental results obtained shows better prediction performance could be achieved using the soft computing techniques (genetic algorithm, fuzzy c-means clustering and random forest classifier)