First check after SageMaker Model Monitor flags feature drift
MLA-C02
Operating, Monitoring, and Securing ML and AI Solutions
Medium
Question 17 of 30
An ML engineer uses Amazon SageMaker Model Monitor to monitor a model that is deployed to an Amazon SageMaker AI real-time endpoint. A data quality monitoring schedule reports that three input features have drifted from the training baseline. Endpoint latency and error rates are unchanged. Ground truth labels for recent predictions are already stored in Amazon S3.
Which measurement should the ML engineer make FIRST?
Show answer and explanation
DModel quality metrics against the baseline, using the labels already collected
The labels are already in hand, so model quality metrics measure the thing in question directly: whether predictions became less accurate. Feature attribution drift says which inputs carry more weight without saying whether accuracy followed. Comparing against last month swaps a fixed baseline for a moving one, and schema violations catch malformed inputs, not a shift within valid ranges.
Source: docs.aws.amazon.com/
Anonymous, no account needed. Your tally stays in this browser.