A company has used Amazon SageMaker to deploy a predictive ML model in production. The company is using SageMaker Model Monitor on the model. After a model update, an ML engineer notices data quality issues in the Model Monitor checks. What should the ML engineer do to mitigate the data quality issues that Model Monitor has identified?
Select an option, then click Submit answer.
Reference / correct answer:
Create a new baseline from the latest dataset. Update Model Monitor to use the new baseline for evaluations.
Most accepted answer: C. Create a new baseline from the latest dataset. Update Model Monitor to use the new baseline for evaluations.
Community votes: C=5, D=2
Selected Answer: D This question lacks sufficient context. If Model Monitor is getting errors after the update, do you want to C) establish that as the new baseline or D) retrain the model to adhere to the existing baseline? I'm going to choose D as there's no indicating we should "change the way we do business" by establishing a new model monitor baseline to conform with the new model's behavior. My $.02 upvoted 1 times
Selected Answer: C Agree with C. upvoted 1 times
Selected Answer: C Amazon SageMaker Model Monitor: Continuously monitors model endpoints to detect issues like: Data quality drift Model quality drift Bias drift Feature attribution drift Baseline: Model Monitor compares incoming data against a baseline dataset that represents "normal" or expected data distributions. If the data distribution changes after a model update, the old baseline may no longer be valid—leading to false positives in data quality issues. upvoted 2 times
Selected Answer: C agree with GiorgioGss - If the problems start appearing "After a model update" then C is the only valid option. upvoted 2 times
Selected Answer: D the model needs to be retrained upvoted 2 times
