부산대학교 도서관

In the field of software engineering, the detection of fault in the software has become a major topic to explore. With the help of data mining and machine learning approaches, this paper aims to denote whether a software is fault prone or not. In order to accomplish that this paper gives importance to compare between different machine learning approaches and by observing their performances we can conclude which models perform better to detect fault in the selected software modules. The dataset we have chosen to work on has imbalanced data. This paper research also worked with the imbalanced dataset and what results the imbalanced dataset gave when examined. The accuracy comparison, the performance of the different metrics can broadly help in software defect detection mechanism.