Unsupervised Detection of Anomalous Commits in Software Repositories

Identifying anomalous commits is essential for maintaining software quality and reliability, as these anomalies can indicate potential issues in code, development practices, or repository management. Current anomaly detection methods typically rely on prede-fined rules or supervised learning, which suffer from limitations such as dependence on labeled datasets, rigid rule definitions, and high maintenance overhead in rapidly evolving repositories. This paper introduces a novel unsupervised framework for effectively detecting anomalous commits without requiring labeled data or rigid rules, providing a scalable and adaptable solution to enhance code quality in modern version control systems. To address the high-dimensional and mul-tifaceted nature of commit data, our approach com-bines dimensionality reduction techniques with tar-geted feature engineering, enhancing both precision and adaptability in anomaly detection. We systematically evaluate three state-of-the-art unsupervised techniques-Local Outlier Factor (LOF), Isolation Forest (IF), and Histogram-Based Outlier Score (HBOS)-across five diverse open-source repositories. Our results demonstrate that Isolation Forest achieves the highest detection accuracy, effectively balancing precision and recall while capturing both global and local anomalies. Additionally, expert validation confirms the practical relevance of our approach, providing insights into frequent and high-impact anomalies encountered in real-world repositories.

• Publication year

  2025

• Venue

  2025 IEEE International Conference on Software Services Engineering (SSE)

• Publication date

  2025-07-07

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/SSE67621.2025.00013
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unsupervised anomaly detection algorithms on real-world data: how many do we need?

  2023cited by this paper
• The Effect of Hyperparameter Tuning on the Comparative Evaluation of Unsupervised Anomaly Detection Methods

  2021cited by this paper
• Anomalicious: Automated Detection of Anomalous and Potentially Malicious Commits on GitHub

  2021cited by this paper
• Benchmarking Unsupervised Outlier Detection with Realistic Synthetic Data

  2020cited by this paper
• The Importance of Data Cleaning: Three Visualization Examples

  2020cited by this paper
• PyOD: A Python Toolbox for Scalable Outlier Detection

  2019cited by this paper
• Quantitative comparison of unsupervised anomaly detection algorithms for intrusion detection

  2019cited by this paper
• On normalization and algorithm selection for unsupervised outlier detection

  2019cited by this paper
• A comparative evaluation of outlier detection algorithms: Experiments and analyses

  2018cited by this paper
• PyDriller: Python framework for mining software repositories

  2018cited by this paper
• Identifying unusual commits on GitHub

  2018cited by this paper
• Boosting Automatic Commit Classification Into Maintenance Activities By Utilizing Source Code Changes

  2017cited by this paper
• Unusual Events in GitHub Repositories

  2017cited by this paper
• Principal component analysis: a review and recent developments

  2016cited by this paper
• On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study

  2016cited by this paper
• A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data

  2016influential reference
• UEDashboard: awareness of unusual events in commit histories

  2015cited by this paper
• Feature Selection and Classification of Microarray Data using MapReduce based ANOVA and K-Nearest Neighbor

  2015cited by this paper
• Commit guru: analytics and risk prediction of software commits

  2015cited by this paper
• Normalization: A Preprocessing Stage

  2015cited by this paper
• A Meta-Analysis of the Anomaly Detection Problem

  2015cited by this paper
• Isolation-Based Anomaly Detection

  2012cited by this paper
• Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm

  2012cited by this paper
• Isolation Forest

  2008cited by this paper
• What's a Typical Commit? A Characterization of Open Source Software Repositories

  2008cited by this paper
• How many bins should be put in a regular histogram

  2006cited by this paper
• Efficient Feature Selection via Analysis of Relevance and Redundancy

  2004influential reference
• LOF: identifying density-based local outliers

  2000cited by this paper

• No citing papers are available for this paper.