Integrated Approach to Software Defect Prediction

Software defect prediction provides actionable outputs to software teams while contributing to industrial success. Empirical studies have been conducted on software defect prediction for both cross project and within-project defect prediction. However, existing studies have yet to demonstrate a method of predicting the number of defects in an upcoming product release. This paper presents such a method using predictor variables derived from the defect acceleration, namely, the defect density, defect velocity, and defect introduction time, and determines the correlation of each predictor variable with the number of defects. We report the application of an integrated machine learning approach based on regression models constructed from these predictor variables. An experiment was conducted on ten different data sets collected from the PROMISE repository, containing 22 838 instances. The regression model constructed as a function of the average defect velocity achieved an adjusted R-square of 98.6%, with a p-value of < 0.001. The average defect velocity is strongly positively correlated with the number of defects, with a correlation coefficient of 0.98. Thus, it is demonstrated that this technique can provide a blueprint for program testing to enhance the effectiveness of software development activities.