A demand-forecasting model is running in production.
Seasonal and customer behavior changes may reduce prediction quality.
Choose two appropriate continuous monitoring activities.
Production monitoring should cover input distribution changes and, when labels arrive, the resulting prediction performance.
Detailed explanation
Input changes can indicate data drift and trigger reassessment.
Input changes can indicate data drift and trigger reassessment.
Accuracy or error can be measured once real outcomes are known.
Accuracy or error can be measured once real outcomes are known.
Production conditions change, so ongoing monitoring is needed.
Production conditions change, so ongoing monitoring is needed.
A name change detects neither drift nor performance loss.
A name change detects neither drift nor performance loss.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01ガイドのDomain 1.3で、モデル監視とドリフトの説明を確認する。Expected result
入力分布と実績に基づく予測性能を別々の監視対象として説明できる。Key points
- Data drift
- Prediction performance
- Continuous monitoring
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.