Evaluating the Predictive Power of Software Metrics for Fault Localization
Fault localization remains a critical challenge in software engineering, directly impacting debugging efficiency and software quality. This study investigates the predictive power of various software metrics for fault localization by framing the task as a multi-class classification problem and evalu...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/14/6/222 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849431860871954432 |
|---|---|
| author | Issar Arab Kenneth Magel Mohammed Akour |
| author_facet | Issar Arab Kenneth Magel Mohammed Akour |
| author_sort | Issar Arab |
| collection | DOAJ |
| description | Fault localization remains a critical challenge in software engineering, directly impacting debugging efficiency and software quality. This study investigates the predictive power of various software metrics for fault localization by framing the task as a multi-class classification problem and evaluating it using the Defects4J dataset. We fitted thousands of models and benchmarked different algorithms—including deep learning, Random Forest, XGBoost, and LightGBM—to choose the best-performing model. To enhance model transparency, we applied explainable AI techniques to analyze feature importance. The results revealed that test suite metrics consistently outperform static and dynamic metrics, making them the most effective predictors for identifying faulty classes. These findings underscore the critical role of test quality and coverage in automated fault localization. By combining machine learning with transparent feature analysis, this work delivers practical insights to support more efficient debugging workflows. It lays the groundwork for an iterative process that integrates metric-based predictive models with large language models (LLMs), enabling future systems to automatically generate targeted test cases for the most fault-prone components, which further enhances the automation and precision of software testing. |
| format | Article |
| id | doaj-art-ca95ec42e9354fa287f46b3e4de7ff02 |
| institution | Kabale University |
| issn | 2073-431X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-ca95ec42e9354fa287f46b3e4de7ff022025-08-20T03:27:30ZengMDPI AGComputers2073-431X2025-06-0114622210.3390/computers14060222Evaluating the Predictive Power of Software Metrics for Fault LocalizationIssar Arab0Kenneth Magel1Mohammed Akour2Adrem Data Laboratory, Department of Computer Science, University of Antwerp, 2020 Antwerpen, BelgiumFaculty of Computer Science, North Dakota State University, Fargo, ND 58108, USACollege of Computer and Information Sciences, Prince Sultan University, Riyadh 12435, Saudi ArabiaFault localization remains a critical challenge in software engineering, directly impacting debugging efficiency and software quality. This study investigates the predictive power of various software metrics for fault localization by framing the task as a multi-class classification problem and evaluating it using the Defects4J dataset. We fitted thousands of models and benchmarked different algorithms—including deep learning, Random Forest, XGBoost, and LightGBM—to choose the best-performing model. To enhance model transparency, we applied explainable AI techniques to analyze feature importance. The results revealed that test suite metrics consistently outperform static and dynamic metrics, making them the most effective predictors for identifying faulty classes. These findings underscore the critical role of test quality and coverage in automated fault localization. By combining machine learning with transparent feature analysis, this work delivers practical insights to support more efficient debugging workflows. It lays the groundwork for an iterative process that integrates metric-based predictive models with large language models (LLMs), enabling future systems to automatically generate targeted test cases for the most fault-prone components, which further enhances the automation and precision of software testing.https://www.mdpi.com/2073-431X/14/6/222fault localizationsoftware quality assurancemachine learningsoftware metricstest coverageautomated debugging |
| spellingShingle | Issar Arab Kenneth Magel Mohammed Akour Evaluating the Predictive Power of Software Metrics for Fault Localization Computers fault localization software quality assurance machine learning software metrics test coverage automated debugging |
| title | Evaluating the Predictive Power of Software Metrics for Fault Localization |
| title_full | Evaluating the Predictive Power of Software Metrics for Fault Localization |
| title_fullStr | Evaluating the Predictive Power of Software Metrics for Fault Localization |
| title_full_unstemmed | Evaluating the Predictive Power of Software Metrics for Fault Localization |
| title_short | Evaluating the Predictive Power of Software Metrics for Fault Localization |
| title_sort | evaluating the predictive power of software metrics for fault localization |
| topic | fault localization software quality assurance machine learning software metrics test coverage automated debugging |
| url | https://www.mdpi.com/2073-431X/14/6/222 |
| work_keys_str_mv | AT issararab evaluatingthepredictivepowerofsoftwaremetricsforfaultlocalization AT kennethmagel evaluatingthepredictivepowerofsoftwaremetricsforfaultlocalization AT mohammedakour evaluatingthepredictivepowerofsoftwaremetricsforfaultlocalization |