Software Defect Prediction Using Non-Negative Matrix Factorization

Quality is considered as an important issue in the fields of software engineering. However, building quality software is very expensive, in order to raise the effectiveness and efficiency of quality assurance and testing, software defect prediction is used to identify defect-prone modules in an upcoming version of a software system and help to allow the effort on those modules. Although many models have been proposed, this problem has not resolved thoroughly. For overcoming these limits, recent results show that researcher should pay more attention to improve the quality of the data. Aimed at this purpose, in this paper, we propose a novel approach to resolve the problem of software defect prediction. The method is classification using Non-Negative Matrix Factorization (NMF). In this paper, NMF algorithm is not only used for extracting external features but also as a powerful way for classification of software defect data. Experiments demonstrating the efficiency of the proposed approach are performed for software defect data classification. And the results show that it outperforms the state of the art techniques tested for this experiment. Finally, we suggest that it can be a useful and practical way addition to the framework of software quality prediction.