A licensing desk captures hourly wait-time scores all day. True wait times are keyed the next morning. A model-quality monitor that runs at midnight always fails or scores an empty label set. What should they do?
Select an answer to reveal the explanation.
Short Explanation
True wait times land the next morning, so a midnight model-quality job scores an empty label set. Gate or reschedule that job until labels can be merged. A data-quality job on captured inputs can still run immediately.
Full Explanation
A model-quality monitor compares predictions with ground truth, so it must run only after labels can be merged. A data-quality job can still analyze captured inputs immediately and does not wait on labels. An empty label set is a failed or meaningless quality run, not a perfect score. Textract is not that merge step, and turning off capture removes the predictions the quality job later needs.