You must explain which features drove a prediction. Which tool helps?
Why D is the answer
SageMaker Clarify
Clarify provides feature attribution as well as bias checks.
In detail
- Clarify explains which features drove a prediction.
- AWS closed SageMaker Clarify to new customers. Existing customers can keep using it.
- Feature attribution works per prediction.
Use case
An illustrative scenario, not a real incident.
A lender must explain a rejection, and Clarify shows which features drove it.
See it in different ways
mindmap
root((SageMaker AI))
Data
Data Wrangler
Ground Truth
Clarify
Train
JumpStart
Automatic model tuning
Debugger
Deploy
Pipelines
Model Registry
Operate
Model Monitorflowchart LR S0["Prediction"] --> S1["Clarify attribution"] --> S2["Top features"]
Key point: Clarify explains predictions.
Why the other options are wrong
- A. SageMaker Debugger
- Debugger inspects training.
- B. SageMaker Model Registry
- The registry tracks versions.
- C. Amazon CloudWatch
- CloudWatch shows metrics.