1.2Standard
Some production fields are missing.
Treat missingness meaningfully.
Choose two practices.
× Incorrect
Investigate cause, rate, time, and group differences; fit imputation on training data and design flags, rejection, or human review.
Detailed explanation
IncorrectReplacing every value by the mean loses no information
Meaning and distribution are hidden.
CorrectFit imputation on training data and use missing flags or rejection when appropriate
Production gaps are handled.
IncorrectContinue predictions without monitoring rising missingness
Data degradation is missed.
CorrectInvestigate cause, rate, time, and group differences and business meaning
Blind imputation is avoided.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.2の欠損値、データ品質、異常入力を確認する。
Official references
What to confirm
欠損を単純な数値置換で終わらせず、意味と本番の異常処理を設計できる。
Key points
- Missing value
- Imputation
- Reject
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
Missing-value imputation
Replacing an absent value with a rule or estimate derived from available data.
Missingness indicator
A feature recording that an original value was absent.
Question IDAWS-AIF-455
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