Equalized Odds

A fairness criterion requiring that an AI model's true positive rate and false positive rate are equal across protected groups.

A fairness check that asks: does the AI make the same types of mistakes equally across groups? It shouldn't be more likely to wrongly flag one group while giving another group a free pass.

This metric is particularly important for high-stakes AI decisions in areas like lending, hiring and insurance. Governance frameworks should specify when equalized odds is the appropriate fairness standard and how it will be measured.