AWS Certified Machine Learning Engineer – Associate (MLA-C01) — Question 79

A company has developed a new ML model. The company requires online model validation on 10% of the traffic before the company fully releases the model in production. The company uses an Amazon SageMaker endpoint behind an Application Load Balancer (ALB) to serve the model.
Which solution will set up the required online validation with the LEAST operational overhead?

Answer options

• A. Use production variants to add the new model to the existing SageMaker endpoint. Set the variant weight to 0.1 for the new model. Monitor the number of invocations by using Amazon CloudWatch.
• B. Use production variants to add the new model to the existing SageMaker endpoint. Set the variant weight to 1 for the new model. Monitor the number of invocations by using Amazon CloudWatch.
• C. Create a new SageMaker endpoint. Use production variants to add the new model to the new endpoint. Monitor the number of invocations by using Amazon CloudWatch.
• D. Configure the ALB to route 10% of the traffic to the new model at the existing SageMaker endpoint. Monitor the number of invocations by using AWS CloudTrail.

Correct answer: A

Explanation

Option A is correct because it allows for online validation by setting the variant weight to 0.1, directing 10% of traffic to the new model with minimal overhead. Option B incorrectly assigns a weight of 1, which would send all traffic to the new model instead of the required 10%. Option C involves creating a new endpoint, which increases operational complexity. Option D suggests using the ALB for traffic routing, which is not the most efficient method compared to using production variants in SageMaker.