Design and implementation of hybrid phase based ensemble technique for defect discovery using SDLC software metrics

Abstract

In recent years, data mining algorithm have been successfully applied in software defects and metrics prediction throughout the software development life cycle (SDLC). Features dependencies and class imbalance are the two main issues in the traditional Bayesian models for defect prediction. Traditional supervised models build high prediction rate with limited single product defect and metric data. Various models have been introduced in the literature to establish a common framework for defect and metric prediction in academia, standards and industry, but none of them are accepted as a common tool in real-time software products. Also, predicting the defects cum metrics in multiple products is one of the common problems in real time associated products. In this proposed model, a new ensemble defect prediction classification model was implemented on multiple associated products to predict metric relationship, along with defects patterns. Experimental results show that proposed model has high true positive rate compare to traditional Bayesian network models.