A service has different outcomes by age and region.
Averages may hide a subgroup affected by both.
Choose two responses.
Measure relevant intersections with sample sizes and uncertainty, check label quality, and investigate mitigation with affected stakeholders.
Detailed explanation
Combined subgroup impact may differ from marginal averages.
Combined subgroup impact may differ from marginal averages.
Measurement and remedy need context.
Measurement and remedy need context.
Harm to an intersectional subgroup can disappear.
Harm to an intersectional subgroup can disappear.
The unmeasured impact remains unknown.
The unmeasured impact remains unknown.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 4.1の公平性、サブグループ、プライバシーを確認する。Expected result
複合属性による不利益と、小集団の評価上の注意を説明できる。Key points
- Intersectional group
- Sample size
- Fairness
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.