This paper reviews recent developments in the use of machine learning methods for predicting software faults to enhance software reliability and quality. To address the various challenges concerning software fault prediction, we conducted a review of 45 articles published between 2023 and 2025 from IEEE, Springer, ACM, and ScienceDirect digital libraries. The paper covers topics such as factors influencing software fault prediction, prediction techniques, datasets and software metrics, evaluation metrics, model selection criteria, and challenges associated with current solutions. The results indicate that Support Vector Machine and Random Forest are superior in terms of accuracy, precision, recall, and F1-score. The use of public datasets, particularly those from the PROMISE and NASA Metric Data Program repositories containing product metrics, is widespread and contributes to improved model performance. The purpose of this study is to advance research in software fault prediction and support the development of high-quality software products by improving defect predictability. This review will be useful to researchers, as it presents the latest overview of the existing literature on software defect prediction.
Aggarwal et al. (Wed,) studied this question.