Fairlearn: Assessing and Improving Fairness of AI Systems
This work addresses fairness issues in AI systems for practitioners, but it is incremental as it builds on existing fairness concepts and tools.
The authors tackled the problem of fairness in AI systems by developing Fairlearn, an open-source Python library that enables practitioners to evaluate model outputs across different populations and includes algorithms for mitigating fairness issues, resulting in a tool that integrates learning resources to address fairness as a sociotechnical challenge.
Fairlearn is an open source project to help practitioners assess and improve fairness of artificial intelligence (AI) systems. The associated Python library, also named fairlearn, supports evaluation of a model's output across affected populations and includes several algorithms for mitigating fairness issues. Grounded in the understanding that fairness is a sociotechnical challenge, the project integrates learning resources that aid practitioners in considering a system's broader societal context.