A deep ensemble learning method for effort-aware just-in-time defect prediction

Since the introduction of Just-in-Time effort aware defect prediction, many researchers are focusing on evaluating the different learning methods for defect prediction. To predict the changes that are defect-inducing, it is im-portant for learning model to consider the nature of the dataset, its imbalance properties and the correlation between different attributes. In this paper, we evaluated the importance of dataset properties, and proposed a novel methodology for learning the effort aware just-in-time defect prediction model. We form an ensemble classifier, which consider the output of three individuals classifier i.e. Random forest, XGBoost and Deep Neural Network. Our proposed methodology shows better performance with 77% accuracy on sample dataset and 81% accuracy on different dataset.