Abstract
Software fault prediction is a valuable exercise in software quality assurance to best allocate limited testing resources. Classification is one of the effective methods for software fault prediction. The classification models are trained based on the datasets obtained by mining software historical repositories. However, the performance of the models depends on the quality of datasets. In this paper, we propose a novel two-stage data preprocessing approach which incorporates both feature selection and instance reduction. Specifically, in the feature selection stage, we first perform relevance analysis, and then propose a threshold-based clustering method, called novel threshold-based clustering algorithm, to conduct redundancy control. In the instance reduction stage, we apply random under-sampling to keep the balance between the faulty and non-faulty instances. In empirical studies, we chose datasets from real-world software projects, such as Eclipse and NASA. Then we compared our approach with some classical baseline methods, and further investigated the influencing factors in our approach. The final results demonstrate the effectiveness of our approach, and provide a guideline for achieving cost-effective data preprocessing when using our two-stage approach.
I. INTRODUCTION
SOFTWARE fault prediction (SFP) is a hot research topic in the domain of software engineering [1]–[17]. It can allocate the limited test resources effectively by predicting the fault proneness of software modules. Classification is one of the prevalent methods used for software fault prediction. Its main task is to categorize modules, represented by a set of software metrics, into two classes: fault-prone (FP), or non-fault-prone (NFP). For a specific classification model, the classifier should be trained in advance based on the training data obtained by mining historical software repositories, such as change logs in software configuration management, bug reports in bug tracking systems, and the e-mails of developers.
VI. CONCLUSION
In this paper, we provide a two-stage data preprocessing approach, which incorporates both feature selection and instance reduction, to improve the quality of software datasets used by classification models for software fault prediction. In the feature selection stage, we propose a novel algorithm which involves both relevance analysis and redundancy control. In the instance reduction stage, we apply random under-sampling to keep the balance between the faulty and non-faulty instances. We systematically design experiments based on the Eclipse and NASA datasets, and compare our approach to other commonly used data preprocessing methods. The results demonstrate the potential of our approach in enhancing the prediction performance of the classifiers built thereafter.
