Software Defect Prediction based on Bayesian Optimization Random Forest
Yingyan Shen, Shaojie Hu, Siqi Cai, Mincheng Chen · 2022 9th International Conference on Dependable Systems and Their Applications (DSA) · 2022
Software defect prediction is an important way to make rational use of software testing data resources and improve software performance. However, people have used a variety of machine learning algorithms to establish defect prediction models, their parameter selection is still a problem. To solve this problem, the software defect prediction method based on Bayesian optimization random forest is proposed. This method preproccess data firstly, and then the Bayesian optimization algorithm is used to tune the hyperparameters of the random forest model. Finally the NASA MDP datasets are used for simulation verification. The experimental results show that our model has better performance for software defect prediction.