Description

Software metrics and fault data belonging to a previous software version are used to build the software fault prediction model for the next release of the software. However there are certain cases when previous fault data are not present. In other words predicting the fault-proneness of program modules when the fault labels for modules are unavailable is a challenging task frequently arised in the software industry There is need to develop some methods to build the software fault prediction model based on unsupervised learning which can help to predict the fault–proneness of a program modules when fault labels for modules are not present. One of the methods is use of clustering techniques. Unsupervised techniques like clustering may be used for fault prediction in software modules, more so in those cases where fault labels are not available. In this study, we propose a Fuzzy c-means clustering based software fault prediction approach for this challenging problem.