Issue Auto-Assignment in Software Projects with Machine Learning Techniques

TL;DR

This paper reports on an industrial initiative applying machine learning techniques to automate issue assignment in a global electronics company, aiming to reduce time and errors, and provides insights from literature review and practical lessons.

Contribution

It presents an industrial case study, compares different algorithms, and shares lessons learned, filling a gap between research and practical application in issue auto-assignment.

Findings

Machine learning can effectively assist issue assignment.

Different algorithms have varying performance in industrial contexts.

Lessons learned can guide future industrial auto-assignment projects.

Abstract

Usually, managers or technical leaders in software projects assign issues manually. This task may become more complex as more detailed is the issue description. This complexity can also make the process more prone to errors (misassignments) and time-consuming. In the literature, many studies aim to address this problem by using machine learning strategies. Although there is no specific solution that works for all companies, experience reports are useful to guide the choices in industrial auto-assignment projects. This paper presents an industrial initiative conducted in a global electronics company that aims to minimize the time spent and the errors that can arise in the issue assignment process. As main contributions, we present a literature review, an industrial report comparing different algorithms, and lessons learned during the project.