MLA-C01 · Question #217
A healthcare company uses an Amazon SageMaker AI endpoint to host a model that predicts patient readmission risk to hospitals. The company wants to predict patient readmissions with high accuracy…
The correct answer is A. Promote the shadow variant to full production. The business objective prioritizes identifying as many true readmissions as possible and explicitly tolerates false positives. Higher recall directly supports this goal, even with lower precision. After a month of successful shadow testing on live traffic, promoting the new…
Question
A healthcare company uses an Amazon SageMaker AI endpoint to host a model that predicts patient readmission risk to hospitals. The company wants to predict patient readmissions with high accuracy and is willing to tolerate false positives. The current model performance has degraded over the previous year. The company trains and deploys a new model as a shadow variant for testing on live traffic from hospitals. The company monitors the performance of the new model for a month. During the month of testing, the shadow variant has a higher recall than the existing model but has a lower precision. What should the company do next?
Options
- APromote the shadow variant to full production.
- BExtend the shadow testing period to capture more data. Monitor the new model to determine
- CUse a blue/green deployment strategy to allocate a small percentage of traffic to the shadow
- DDisable the shadow variant and roll back to the main variant.
How the community answered
(63 responses)- A68% (43)
- B17% (11)
- C5% (3)
- D10% (6)
Explanation
The business objective prioritizes identifying as many true readmissions as possible and explicitly tolerates false positives. Higher recall directly supports this goal, even with lower precision. After a month of successful shadow testing on live traffic, promoting the new model to production is the appropriate next step.
Topics
Community Discussion
No community discussion yet for this question.