What question did this study set out to answer?

This study aims to consolidate fairness definitions and identify major problem types in machine learning software.

April 30, 2026Open Access

Software Unfairness Detection in Machine Learning-Based Systems: A Systematic Mapping Study

Key Points

This study aims to consolidate fairness definitions and identify major problem types in machine learning software.
Conducted a systematic mapping of literature on software unfairness detection in machine learning systems.
Included 67 primary studies after quality assessment from an initial pool of 1805 records across digital libraries.
Reviewed various testing approaches and commonly used datasets related to fairness.
Research activity on fairness detection in machine learning has significantly increased, especially since 2019.
The majority of studies focus on existing fairness methods and bias mitigation strategies.
Integration testing is the most common testing level, with notable use of datasets like COMPAS and Adult Census Income.

Abstract

Machine learning-based systems are increasingly deployed in high-stakes domains, such as healthcare, finance, law, and e-commerce, where their predictions directly influence critical decisions. Although these systems offer powerful data-driven support, they also introduce serious concerns related to fairness, bias, and discrimination. As a result, detecting and addressing unfairness in machine learning software has become a central research challenge. This study presents a systematic mapping of research on software unfairness detection in machine learning systems, with the aim of consolidating existing fairness definitions, identifying major problem types, examining testing approaches, reviewing commonly used datasets, and highlighting open research gaps. A structured search was conducted across five major digital libraries and additional sources, covering publications from 2010 to 2025. From 1805 initially identified records, 67 primary studies met the inclusion and quality assessment criteria. The findings show that research activity has grown significantly since 2019, reaching a peak in 2022. Most studies were published in conference proceedings, accounting for 52% of the primary studies, followed by journals and workshop proceedings, which accounted for 42% and 6% of the primary studies. The literature encompasses multiple research themes, with 36% of the primary studies focusing on the analysis of existing fairness methods, 22% addressing bias mitigation strategies, 30% investigating testing techniques, and 12% proposing or evaluating evaluation frameworks. Fairness testing was conducted across multiple testing levels, including unit, integration, and system testing. Integration-level testing was the most prevalent, accounting for approximately 37.9% of the studies, followed by system-level testing at 27.3% and unit-level testing at 12.1%. Additionally, 22.7% of the studies applied fairness testing across more than one testing level. Frequently used datasets included COMPAS, Adult Census Income, and German Credit. Widely adopted tools, such as IBM AI Fairness 360, Themis, and Aequitas, were also identified. Overall, the systematic mapping study (SMS) highlights the progress made in fairness research while emphasizing the need for stronger integration of fairness into practical machine learning development.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper