An ML-based Approach to Predicting Software Change Dependencies: Insights from an Empirical Study on OpenStack

2025-08-07

AI Summary

Implicit dependencies between software changes are often identified too late—51.08% of such dependencies in OpenStack are discovered only during code review, with an average delay of 5.06 hours—causing build failures and deployment delays. Method: We propose a machine learning–based semi-automated dependency prediction approach. It introduces the first empirical analysis revealing bottlenecks in cross-team/component dependency discovery and employs a dual-model architecture: one model estimates the probability of dependency between change pairs, while the other precisely localizes the specific dependent artifacts. The models jointly leverage historical change metadata, code modification patterns, and developer behavioral features. Evaluation uses AUC and Brier Score. Results: On the OpenStack dataset, the models achieve mean AUCs of 79.33% and 91.89%, with Brier Scores of 0.11 and 0.014, respectively; Top-k recall improves significantly, and average developer dependency identification time drops from 57.12 hours to negligible.

Technology Category

• Machine Learning: Hardware-aware ML
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

As software systems grow in complexity, accurately identifying and managing dependencies among changes becomes increasingly critical. For instance, a change that leverages a function must depend on the change that introduces it. Establishing such dependencies allows CI/CD pipelines to build and orchestrate changes effectively, preventing build failures and incomplete feature deployments. In modern software systems, dependencies often span multiple components across teams, creating challenges for development and deployment. They serve various purposes, from enabling new features to managing configurations, and can even involve traditionally independent changes like documentation updates. To address these challenges, we conducted a preliminary study on dependency management in OpenStack, a large-scale software system. Our study revealed that a substantial portion of software changes in OpenStack over the past 10 years are interdependent. Surprisingly, 51.08% of these dependencies are identified during the code review phase-after a median delay of 5.06 hours-rather than at the time of change creation. Developers often spend a median of 57.12 hours identifying dependencies, searching among a median of 463 other changes. To help developers proactively identify dependencies, we propose a semi-automated approach that leverages two ML models. The first model predicts the likelihood of dependencies among changes, while the second identifies the exact pairs of dependent changes. Our proposed models demonstrate strong performance, achieving average AUC scores of 79.33% and 91.89%, and Brier scores of 0.11 and 0.014, respectively. Indeed, the second model has a good top-k recall across all types of pairs, while the top-k precision has room for improvement.

Problem

• Predicting software change dependencies in complex systems
• Reducing dependency identification delays in CI/CD pipelines
• Improving accuracy of ML-based dependency detection models

Innovation

• ML models predict software change dependencies
• Semi-automated approach reduces dependency identification time
• High AUC scores validate model performance