A Novel Approach for Improving Software Quality Prediction

247 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Pvt. Ltd. Abstract—Software quality prediction is a process of utilizing software metrics such as code-level measurements and defect data to build classification models that are able to estimate the quality of program modules. These kinds of estimations can help software managers to effectively allocate potentially limited project resources, focusing on program modules that are of poor quality or likely to have a high number of faults. However, the effectiveness of such models depends on the quality of training data and also the underlying classification technique used for model calibration. The major problem that affects the quality of training datasets is high dimensionality and class imbalance. These problems can be alleviated by choosing necessary data preprocessing techniques before performing the classification. This paper presents an approach for using feature selection and data sampling together to deal with the problems. In this paper a wrapper based feature selection approach is used as the feature selection method and the ensemble learning method used is RUSBoost, in which random undersampling (RUS) is integrated into a boosting algorithm. The main purpose of this paper is to investigate the impact of feature selection along with RUSBoost approach, on the classification performance in the context of software quality prediction.