fairlearn-fairness

Fairlearn provides "Metrics - Tools to assess which groups are negatively impacted and compare models across fairness and accuracy dimensions" and "Algorithms - Techniques to mitigate unfairness" per the [Fairlearn quickstart]. Two primitives: MetricFrame (group disaggregation) + Reductions (ExponentiatedGradient, ThresholdOptimizer).

When to use

• Pre-deployment: assert per-group accuracy / selection rate disparities are within budget.
• Bias incident triage: a stakeholder reports the model is unfair to group X; produce evidence + a mitigated comparison.
• Compliance evidence (ECOA, GDPR Art. 22, EU AI Act high-risk systems): group-disaggregated metrics + mitigation provenance.

Step 1 - Install