1.2Standard
There is little data and repeated user records.
Compare models reliably.
Choose two practices.
× Incorrect
Respect group and time independence, report mean and variation across folds, and keep a final test set separate.
Detailed explanation
IncorrectTune repeatedly on the final test result
The test becomes contaminated.
CorrectKeep the same user or future rows from leaking across folds
Independence is preserved.
IncorrectRandomly split records from one user across folds
User patterns leak.
CorrectReport mean and variation and retain a separate final test
Uncertainty is visible.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.2の交差検証、グループ分割、時系列評価を確認する。
Official references
What to confirm
データの関係性を保った分割で、評価結果のばらつきを説明できる。
Key points
- Cross-validation
- Group split
- Variation
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
Cross-validation
Repeated training and evaluation across several data partitions.
Group split
A partition that keeps records from one entity in a single fold.
Question IDAWS-AIF-433
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