Building Defect Prediction Models by Online Learning Considering Defect Overlooking

抄録

Building defect prediction models based on online learning can enhance prediction accuracy. It continuously rebuilds a new prediction model while adding new data points. However, a module predicted as “non-defective” can result in fewer test cases for such modules. Thus, a defective module can be overlooked during testing. The erroneous test results are used as learning data by online learning, which could negatively affect prediction accuracy. To suppress the negative influence, we propose to apply a method that fixes the prediction as positive during the initial stage of online learning. Additionally, we improved the method to consider the probability of defect overlooking. In our experiment, we demonstrate this negative influence on prediction accuracy and the effectiveness of our approach. The results show that our approach did not negatively affect AUC but significantly improved recall.