The production distribution for a loan model is changing from training data.
Decide whether the model should be reevaluated.
Choose two appropriate monitoring practices.
Compare feature distributions and track performance over time and across groups to detect drift and its impact.
Detailed explanation
This detects changes in the input distribution.
This detects changes in the input distribution.
The change may affect quality and different groups differently.
The change may affect quality and different groups differently.
Output stability does not prove that input drift is harmless.
Output stability does not prove that input drift is harmless.
Data and business conditions can change after deployment.
Data and business conditions can change after deployment.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01試験ガイドDomain 1.2のモデル監視、データ品質、ドリフトを確認する。Expected result
入力分布と性能を別々に監視し、再評価条件を定義できる。Key points
- Distribution shift
- Performance
- Continuous evaluation
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.