A hiring-support model contains very few examples for one group.
Compare error rates by group before deployment.
What should be done first?
Check data representativeness and design group-level evaluation rather than relying only on an overall average.
Detailed explanation
Removing evaluation attributes can make group differences impossible to measure.
Known data gaps can create unfair impact.
Without representative data, an average can hide unequal impact.
An average can hide disparate error rates.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドのDomain 4.1で公平性、代表性、バイアス評価を確認する。
Official references
What to confirm
代表性、グループ別評価、平均値だけでは不十分な理由を説明できる。
Key points
- Representativeness
- Group evaluation
- Average limitations
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
Aggregate masking
A single average can hide substantially different outcomes among groups.
Evaluation attributes
Attributes may be restricted in decisions yet still needed in protected evaluation data.