A data ethics officer is reviewing fairness metrics for a recidivism prediction model used in bail decisions. The model achieves equal accuracy across racial groups but has different false positive rates. Which fairness criterion is violated?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — equalized odds is correct because it requires both equal true positive rates and equal false positive rates across groups. If false positive rates differ, some groups are more often incorrectly labeled high-risk, so equalized odds is violated even when overall accuracy is equal.
Full Explanation
Equalized odds is correct because it requires both equal true positive rates and equal false positive rates across groups. If false positive rates differ, meaning some groups are more often incorrectly labeled high-risk, equalized odds is violated even when overall accuracy is equal. Demographic parity is wrong because it requires equal positive prediction rates across groups, not equal false positive rates. Equal opportunity is wrong because it requires only equal true positive rates, so differing false positive rates do not violate it. Predictive parity is wrong because it requires equal positive predictive value across groups, not equal false positive rates.