To improve software reliability, software defect prediction is used to find software bugs and prioritize testing efforts. Recently, some researchers introduced deep learning models, such as the deep belief network (DBN) and the state-of-the-art convolutional neural network (CNN), and used automatically generated features extracted from abstract syntax trees (ASTs) and deep learning models to improve defect prediction performance. However, the research on the CNN model failed to reveal clear conclusions due to its limited dataset size, insufficiently repeated experiments, and outdated baseline selection. To solve these problems, we built the PROMISE Source Code (PSC) dataset to enlarge the original dataset in the CNN research, which we named the Simplified PROMISE Source Code (SPSC) dataset. Then, we proposed an improved CNN model for within-project defect prediction (WPDP) and compared our results to existing CNN results and an empirical study. Our experiment was based on a 30-repetition holdout validation and a 10 * 10 cross-validation. Experimental results showed that our improved CNN model was comparable to the existing CNN model, and it outperformed the state-of-the-art machine learning models significantly for WPDP. Furthermore, we defined hyperparameter instability and examined the threat and opportunity it presents for deep learning models on defect prediction.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited