AI0-001 AI Governance and Ethics Practice Question

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  Calibration

  Why it's wrong here

  Equal false positive rates across groups is defined by equalised odds, which constrains true and false positive rates per group; calibration only aligns predicted probabilities with observed outcomes, ignoring error-rate parity. Calibration is the right metric when probability reliability matters, such as risk scores used for pricing or triage.

• ✗

  Individual fairness

  Why it's wrong here

  Individual fairness requires similar predictions for similar individuals, which says nothing about equal false positive rates between groups. It is tempting because it addresses fairness at a personal level, but it would be correct only when consistency between comparable individuals is the stated requirement.

• ✓

  Equalized odds

  Why this is correct

  Equalized odds requires true positive and false positive rates to match across demographic groups, directly satisfying the board's constraint of equal false positive rates. Unlike demographic parity, which only equalises positive prediction rates, it conditions on the actual outcome, making it the precise metric for sentencing recommendations where unequal errors cause harm.

• ✗

  Demographic parity

  Why it's wrong here

  Demographic parity equalises positive prediction rates across groups, regardless of actual outcomes, so it does not equalise false positive rates. It is tempting as a broad group-fairness measure, but it would be correct only when selection rates, not error rates, must match between demographics.