AI0-001 AI Governance and Ethics Practice Question
An AI model for skin cancer detection achieves high accuracy but performs poorly on dark skin tones. The team wants to evaluate whether the model is calibrated across skin tones. Which fairness metric should they use?
⚠ Common exam trap
The AI0-001 exam often tests the distinction between fairness metrics by presenting a scenario where 'accuracy' is high but subgroup performance differs, and candidates mistakenly choose equalized odds or demographic parity instead of recognizing that the core issue is confidence score reliability, i.e., calibration.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Calibration
Calibration is the correct metric because it directly measures whether the predicted probabilities of skin cancer match the actual outcomes across different skin tones. A model can have high overall accuracy but be miscalibrated for a subgroup if its confidence scores are systematically over- or under-confident for that group. In this scenario, the team needs to check if the model's risk scores are equally reliable for dark skin tones as for light skin tones, which is exactly what calibration assesses.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Equalised odds
Why it's wrong here
Equalised odds equalises true positive and false positive rates across groups, addressing error-rate parity rather than whether predicted probabilities match observed malignancy rates within each skin tone. It is tempting because it targets group error disparities, and would be correct if the goal were equal sensitivity and specificity across skin tones.
- ✗
Demographic parity
Why it's wrong here
Demographic parity equalises positive prediction rates across groups, ignoring whether predicted probabilities match observed outcomes, so it cannot detect miscalibration across skin tones. It is tempting because it is the standard metric for equal selection rates in hiring or lending, where balanced approval proportions matter more than probability accuracy.
- ✗
Individual fairness
Why it's wrong here
Individual fairness requires similar treatment for similar individuals, which demands a defined similarity metric and says nothing about whether predicted probabilities match actual outcomes per skin tone. It is tempting for auditing pairwise consistency in recommendation or ranking systems, not for measuring calibration across demographic groups.
- ✓
Calibration
Why this is correct
Calibration measures whether predicted probabilities match observed outcomes within each group, so comparing calibration curves across skin tones directly tests whether confidence scores are equally reliable. It isolates probability reliability, unlike equalised odds or demographic parity, which assess error or selection rates instead.
About these practice questions
Courseiva writes every AI0-001 question from scratch — 962 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.