What the study found
The review found that Support Vector Machine and Random Forest were the strongest methods among the studies it examined, based on accuracy, precision, recall, and F1-score. It also found that public datasets, especially PROMISE and NASA Metric Data Program data, were widely used.
Why the authors say this matters
The authors say the review is meant to advance research in software fault prediction and support the development of high-quality software products by improving defect predictability. They also state that it provides a recent overview of the literature for researchers.
What the researchers tested
The authors reviewed 45 articles published between 2023 and 2025 from IEEE, Springer, ACM, and ScienceDirect. The review covered factors affecting software fault prediction, prediction techniques, datasets and software metrics, evaluation metrics, model selection criteria, and current challenges.
What worked and what didn't
Across the reviewed studies, Support Vector Machine and Random Forest had better reported performance than other methods on the metrics mentioned in the abstract. The abstract also says that using public datasets, particularly PROMISE and NASA Metric Data Program repositories, was common and contributed to improved model performance.
What to keep in mind
This is a review of published studies, not a new fault-prediction experiment. The abstract does not describe detailed limitations beyond noting that current solutions still face challenges.
Key points
- The review covered 45 articles published from 2023 to 2025.
- Support Vector Machine and Random Forest were reported as the top-performing methods.
- PROMISE and NASA Metric Data Program datasets were widely used.
- The review included factors, techniques, datasets, metrics, model selection criteria, and challenges.
- The authors say the review supports research and software quality improvement.
Disclosure
- Research title:
- Review finds SVM and Random Forest perform best in software fault prediction
- Authors:
- Ruchika Aggarwal, Kamaljit Kaur
- Institutions:
- Altran (France), Altran (France), Sri Guru Granth Sahib World University
- Publication date:
- 2026-01-28
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with scholarly research without reading academic papers — one filtered digest, every Friday.