Input distribution is stable but the relationship to outcomes changes.
Investigate degradation.
Choose two checks.
Compare input, prediction, label relationship, and errors over time and check business rules, label definitions, and model versions.
Detailed explanation
Relationship changes can be isolated.
Relationship changes can be isolated.
Causes can be traced.
Causes can be traced.
Concept drift can remain.
Concept drift can remain.
The cause may be wrong.
The cause may be wrong.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 1.2・3.3の概念ドリフト、モデル監視、ラベルを確認する。Expected result
入力分布の変化だけでなく、結果との関係や業務変更を含めてドリフトを調査できる。Key points
- Concept drift
- Label definition
- Time series
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.