A library occupancy model is in front of the board, and staff need which features drove a full score last Saturday. This is post-training explanation, not a Domain 1 pre-training bias report. Which service fits?
Select an answer to reveal the explanation.
Short Explanation
The board wants which features drove last Saturday's full score. SageMaker Clarify does feature attribution on the trained model. The Domain 1 pre-training bias report is a different stop, and Polly or Ground Truth does not explain that score.
Full Explanation
SageMaker Clarify interprets trained-model outputs with feature attribution. That is post-training explainability, not the Domain 1 pre-training data-bias report. Polly and Ground Truth are not that explanation.