A company needs to host a custom ML model to perform forecast analysis. The forecast analysis will occur with predictable and sustained load during the same 2-hour period every day. Multiple invocatio

Question

Options

• ASchedule an Amazon SageMaker batch transform job by using AWS Lambda.
• BConfigure an Auto Scaling group of Amazon EC2 instances to use scheduled scaling.
• CUse Amazon SageMaker Serverless Inference with provisioned concurrency.
• DRun the model on an Amazon Elastic Kubernetes Service (Amazon EKS) cluster on Amazon EC2

• A
  4% (1)
• B
  11% (3)
• C
  81% (22)
• D
  4% (1)

Explanation

Option C is correct because SageMaker Serverless Inference with provisioned concurrency satisfies all three key requirements simultaneously: AWS fully manages the underlying infrastructure and auto scaling, provisioned concurrency keeps the model endpoint "warm" to eliminate cold starts and guarantee quick responses, and the service can be scheduled to have concurrency active only during the predictable 2-hour daily window - optimizing cost without sacrificing performance.

Option A is wrong because batch transform is designed for offline, asynchronous batch processing - not for low-latency, real-time invocations that require quick responses.

Option B is wrong because managing an Auto Scaling group of EC2 instances means the company manages the underlying infrastructure (OS patching, capacity planning, scaling configuration), violating the requirement that AWS handle this.

Option D is wrong for the same reason as B - EKS on EC2 places infrastructure and cluster management responsibility on the customer, not AWS.

Memory tip: Think "3 Ps" for this scenario - Predictable load + Provision concurrency + Purely managed = SageMaker Serverless with provisioned concurrency. Whenever a question demands quick inference responses and zero infrastructure management, provisioned concurrency on a serverless endpoint is the signal to look for.

No community discussion yet for this question.