Integration of Feature Selection with Data Level Approach for Software Defect Prediction

Abstract

The dataset of software metrics in general are not balanced (unbalanced).An imbalance distribution of classes and attributes that are not relevant may decrease the performance of the model prediction software defect, because the majority of the class predictions tend to produce than minority class. This research uses a public dataset from NASA (National Aeronautics and Space Administration) MDP (Metrics Data Program) repository. This research aims to reduce the influence of class imbalance in the dataset, so that performance can be improved in the classification of defect prediction software. The model proposed in this research is applying the technique feature selection with particle swarm optimization (PSO), approaches the level of data using Random Under Sampling (RUS) and SMOTE (Synthetic Minority Over-sampling Technique) and (ensemble) Bagging with Naive Bayes Classifier. Research results show that the proposed model can improve the performance of naive bayes of the overall value of the AUC reached > 0.8. Statistical tests indicate that there is a significant difference between a naive bayes model with the model proposed by the p value (0.043) smaller than the alpha values (0.05) which means there is a significant difference between the two models.