A kayak-share demand model may score one zip code systematically worse after training. The official Domain 2 Clarify use is insights into the trained model, not the Domain 1 CI/DPL data report. What should they run?
Select an answer to reveal the explanation.
Short Explanation
One zip code may score systematically worse after training. Run SageMaker Clarify post-training bias and model-insight metrics. The Domain 1 CI/DPL data report is earlier, and Transcribe or K-Means is not that report.
Full Explanation
SageMaker Clarify post-training metrics give bias and model insights on the trained model, which is distinct from Domain 1 pre-training CI/DPL work. Transcribe and K-Means are not that report.