1.2Standard
Use income and age in a distance-based model.
Avoid scale dominating the result.
Choose two practices.
× Incorrect
Learn preprocessing statistics from training data and reproduce the same units, transformations, and missing-value handling at inference.
Detailed explanation
CorrectReproduce the same units, transformations, and missing handling in production
Training and inference meanings align.
IncorrectCompute the mean over all data before splitting
Evaluation information leaks.
IncorrectUse a different unit in production
Feature meaning changes.
CorrectLearn scaling statistics from training data only
Evaluation information does not leak.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.2の特徴量前処理とリーケージを確認する。
Official references
What to confirm
訓練・推論で一貫した特徴量変換を実装できる。
Key points
- Scaling
- Preprocessing
- Consistency
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
Feature scaling
Transforming numeric features so their scales are comparable for a model.
Preprocessing pipeline
An ordered set of transformations applied consistently before training and inference.
Question IDAWS-AIF-317
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