Create fraud features from order history.
Only use information available at prediction time.
Choose two designs.
Compute features from prediction-time history only, manage definitions, units, missing values, and versions, and use the same processing for training and inference.
Detailed explanation
Future information cannot leak.
Future information cannot leak.
Training and inference remain aligned.
Training and inference remain aligned.
Unavailable future data leaks.
Unavailable future data leaks.
Training and inference meanings diverge.
Training and inference meanings diverge.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 1.3の特徴量、データリーケージ、ライフサイクルを確認する。Expected result
特徴量の再現性と未来情報の混入防止を説明できる。Key points
- Feature
- Time
- Leakage
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.