Software Defect Prediction Based On Deep Learning Models: Performance Study
This work addresses software defect prediction for software engineers, but it is incremental as it applies existing deep learning methods to known datasets.
The paper tackled software defect prediction by applying two deep learning models, Stack Sparse Auto-Encoder (SSAE) and Deep Belief Network (DBN), to NASA datasets, finding that SSAE outperformed DBN in most metrics and improved accuracy for datasets with sufficient samples.
In recent years, defect prediction, one of the major software engineering problems, has been in the focus of researchers since it has a pivotal role in estimating software errors and faulty modules. Researchers with the goal of improving prediction accuracy have developed many models for software defect prediction. However, there are a number of critical conditions and theoretical problems in order to achieve better results. In this paper, two deep learning models, Stack Sparse Auto-Encoder (SSAE) and Deep Belief Network (DBN), are deployed to classify NASA datasets, which are unbalanced and have insufficient samples. According to the conducted experiment, the accuracy for the datasets with sufficient samples is enhanced and beside this SSAE model gains better results in comparison to DBN model in the majority of evaluation metrics.