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

TL;DR

This paper presents an empirical study on dependency management in OpenStack and introduces ML models to predict change dependencies, significantly aiding developers in proactive dependency identification and reducing manual effort.

Contribution

The paper offers the first empirical analysis of change dependencies in OpenStack and proposes two ML models that effectively predict dependency likelihood and specific dependent change pairs.

Findings

Over 50% of dependencies are identified during code review after delays.

Developers spend median 57 hours to identify dependencies.

ML models achieve high AUC scores of 79.33% and 91.89%.

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.