1.2Basic
Some production fields are missing.
Missingness itself may carry business meaning.
Choose two designs.
× Incorrect
Monitor missing rates and reasons by field, and reproduce the training-time imputation and missing indicators at inference.
Detailed explanation
CorrectMonitor missing rate, reason, and allowed range by field
Input quality changes become visible.
IncorrectReplace every missing value with zero without checking meaning
Zero may be a real value.
CorrectReproduce the training imputation and missing-value indicator at inference
Feature meaning stays consistent.
IncorrectUse a different imputation method in production
Training and inference diverge.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.2のデータ品質、欠損値、前処理を確認する。
Official references
What to confirm
欠損値を一律処理せず、品質監視と一貫した補完を実装できる。
Key points
- Missing rate
- Imputation
- Indicator
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
An expected data attribute for which no value was recorded.
Imputation
Replacing a missing value with a rule- or model-derived estimate.
Question IDAWS-AIF-333
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