Toolkit developed by Microsoft.
Fairlearn provides developers and data scientists with capabilities to assess the fairness of their machine learning models and mitigate unfairness. Assess existing models and train new models with fairness in mind. Compare models and make trade-offs between fairness and model performance.
It is a Python package that empowers developers of artificial intelligence (AI) systems to assess their system’s fairness and mitigate any observed unfairness issues. Fairlearn contains mitigation algorithms as well as a Jupyter widget for model assessment. The Fairlearn package has two components:
- A dashboard for assessing which groups are negatively impacted by a model, and for comparing multiple models in terms of various fairness and accuracy metrics.
- Algorithms for mitigating unfairness in a variety of AI tasks and along a variety of fairness definitions.
There is also a collection of Jupyter notebooks and an a detailed API guide, that you can check to learn how to leverage Fairlearn for your own data science scenario.
- Fairlearn – A Python package to assess AI system’s fairness – article by Francesca Lazzeri, Microsoft TechCommunity
- Fairlearn: The secret to teaching your models to play fair – article by Willem Meints, published on Medium