An attribute selection process for software defect prediction

Abstract

In software quality research, software defect prediction is a key topic. The characteristics of software attributes influences the performance and effectiveness of the defect prediction model. However this issue is not well explored to the best of our knowledge. Thus we focus on the problem of attribute selection in the context of software defect prediction here and hence in this research, we propose a technique for selecting best set of attributes to improve the accuracy of the software defect prediction. The proposed method is evaluated using the data sets from NASA metric data repository which demonstrate acceptable accuracy using simple algorithm.