Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories
Ensuring reliability, availability, and security in modern software systems hinges on early fault detection, yet predicting which parts of a codebase are most at risk remains a significant challenge. In this paper, we analyze 2.4 million commits drawn from 33 heterogeneous open-source projects, span...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/9/7/174 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839616489990127616 |
|---|---|
| author | Philip König Sebastian Raubitzek Alexander Schatten Dennis Toth Fabian Obermann Caroline König Kevin Mallinger |
| author_facet | Philip König Sebastian Raubitzek Alexander Schatten Dennis Toth Fabian Obermann Caroline König Kevin Mallinger |
| author_sort | Philip König |
| collection | DOAJ |
| description | Ensuring reliability, availability, and security in modern software systems hinges on early fault detection, yet predicting which parts of a codebase are most at risk remains a significant challenge. In this paper, we analyze 2.4 million commits drawn from 33 heterogeneous open-source projects, spanning healthcare, security tools, data processing, and more. By examining each repository per file and per commit, we derive process metrics (e.g., churn, file age, revision frequency) alongside size metrics and entropy-based indicators of how scattered changes are over time. We train and tune a gradient boosting model to classify bug-prone commits under realistic class-imbalance conditions, achieving robust predictive performance across diverse repositories. Moreover, a comprehensive feature-importance analysis shows that files with long lifespans (high age), frequent edits (revision count), and widely scattered changes (entropy metrics) are especially vulnerable to defects. These insights can help practitioners and researchers prioritize testing and tailor maintenance strategies, ultimately strengthening software dependability. |
| format | Article |
| id | doaj-art-7c2ae9f91a3d4dba96aff484f33f83e6 |
| institution | Matheson Library |
| issn | 2504-2289 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj-art-7c2ae9f91a3d4dba96aff484f33f83e62025-07-25T13:14:08ZengMDPI AGBig Data and Cognitive Computing2504-22892025-07-019717410.3390/bdcc9070174Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source RepositoriesPhilip König0Sebastian Raubitzek1Alexander Schatten2Dennis Toth3Fabian Obermann4Caroline König5Kevin Mallinger6SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, AustriaSBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, AustriaInstitute of Information Systems Engineering, TU Wien, Favoritenstrasse 9–11/194, 1040 Vienna, AustriaSBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, AustriaSBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, AustriaChristian Doppler Laboratory for Assurance and Transparency in Software Protection, Research Group Security & Privacy, Faculty of Computer Science, University of Vienna, Kolingasse 14–16, 1040 Vienna, AustriaSBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, AustriaEnsuring reliability, availability, and security in modern software systems hinges on early fault detection, yet predicting which parts of a codebase are most at risk remains a significant challenge. In this paper, we analyze 2.4 million commits drawn from 33 heterogeneous open-source projects, spanning healthcare, security tools, data processing, and more. By examining each repository per file and per commit, we derive process metrics (e.g., churn, file age, revision frequency) alongside size metrics and entropy-based indicators of how scattered changes are over time. We train and tune a gradient boosting model to classify bug-prone commits under realistic class-imbalance conditions, achieving robust predictive performance across diverse repositories. Moreover, a comprehensive feature-importance analysis shows that files with long lifespans (high age), frequent edits (revision count), and widely scattered changes (entropy metrics) are especially vulnerable to defects. These insights can help practitioners and researchers prioritize testing and tailor maintenance strategies, ultimately strengthening software dependability.https://www.mdpi.com/2504-2289/9/7/174fault predictionmachine learningCatBoostcode metricsfeature importanceartificial intelligence |
| spellingShingle | Philip König Sebastian Raubitzek Alexander Schatten Dennis Toth Fabian Obermann Caroline König Kevin Mallinger Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories Big Data and Cognitive Computing fault prediction machine learning CatBoost code metrics feature importance artificial intelligence |
| title | Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories |
| title_full | Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories |
| title_fullStr | Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories |
| title_full_unstemmed | Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories |
| title_short | Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories |
| title_sort | boost classifier driven fault prediction across heterogeneous open source repositories |
| topic | fault prediction machine learning CatBoost code metrics feature importance artificial intelligence |
| url | https://www.mdpi.com/2504-2289/9/7/174 |
| work_keys_str_mv | AT philipkonig boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories AT sebastianraubitzek boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories AT alexanderschatten boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories AT dennistoth boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories AT fabianobermann boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories AT carolinekonig boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories AT kevinmallinger boostclassifierdrivenfaultpredictionacrossheterogeneousopensourcerepositories |