A Catalog of Fairness-Aware Practices in Machine Learning Engineering

TL;DR

This paper systematically catalogs 28 fairness-aware practices across the machine learning lifecycle, providing a comprehensive resource to improve fairness, accountability, and reliability in ML systems for researchers and practitioners.

Contribution

It introduces a novel, systematically derived catalog of fairness practices mapped to ML lifecycle stages, filling a gap in engineering guidance for fairness.

Findings

Identified 28 fairness practices from literature.

Mapped practices onto ML lifecycle stages.

Provided actionable insights for practitioners.

Abstract

Machine learning's widespread adoption in decision-making processes raises concerns about fairness, particularly regarding the treatment of sensitive features and potential discrimination against minorities. The software engineering community has responded by developing fairness-oriented metrics, empirical studies, and approaches. However, there remains a gap in understanding and categorizing practices for engineering fairness throughout the machine learning lifecycle. This paper presents a novel catalog of practices for addressing fairness in machine learning derived from a systematic mapping study. The study identifies and categorizes 28 practices from existing literature, mapping them onto different stages of the machine learning lifecycle. From this catalog, the authors extract actionable items and implications for both researchers and practitioners in software engineering. This work aims to provide a comprehensive resource for integrating fairness considerations into the development and deployment of machine learning systems, enhancing their reliability, accountability, and credibility.