Software Defect Density Prediction Using Deep Learning

Abstract

Delivering a reliable and high-quality software system to client is a big challenge in software development and evolution process. One of the software measures that confirm the quality of the system is the defect density. Practitioners usually need this measure during software development process or during a period of operation to indicate the reliability of software system. However, since predicting defect density before testing the modules is time consuming, managers need to build a prediction model that can help in detecting the defective modules. This process can reduce the testing cost and improve testing resources utilizations. The most intrinsic feature of software defect datasets is the data sparsity in the defect density which might bias the final prediction. Therefore, we use deep learning to build defect density prediction models and handle the inherit challenge of data sparsity in defect density. Deep learning has shown to be effective with sparse data. The constructed model has been evaluated against well-known machine learning methods over 28 public datasets. The obtained results confirmed that the deep learning model is generally more adequate than other machine models over the datasets with high and very high sparsity ratios, and competitive choice when the sparsity ratio is either medium or low.

Keywords

• Defect density prediction
• deep learning
• data sparsity
• machine learning