4.1Standard
Compare approval rates across groups.
Overall performance is high.
Choose two practices.
× Incorrect
Compare group approval and error metrics with sample sizes, uncertainty, label quality, and business impact rather than relying on an overall average.
Detailed explanation
CorrectReport sample size, confidence, label quality, and business impact
Uncertainty and meaning can be judged.
IncorrectExclude groups with differences
Impact becomes unmeasured.
CorrectCompare approval, error, recall, and precision by group
Outcome differences become visible.
IncorrectDeclare fairness from overall accuracy
Group differences can average out.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 4.1の公平性、グループ指標、影響評価を確認する。
Official references
What to confirm
グループごとの結果差を統計的・業務的に評価できる。
Key points
- Fairness
- Group metrics
- Confidence
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Impact disparity
A difference in outcomes or error burdens between defined groups.
Group metric
A performance or outcome measure calculated separately for a population.
Question IDAWS-AIF-360
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue