A company needs to deploy a custom-trained classification ML model on AWS. The model must make near real-time predictions with low latency and must handle variable request volumes. Which solution…

Question

Options

• ACreate an Amazon SageMaker AI batch transform job to process inference requests in batches.
• BUse Amazon API Gateway to receive prediction requests. Use an Amazon S3 bucket to host and
• CDeploy an Amazon SageMaker AI endpoint. Configure auto scaling for the endpoint.
• DLaunch AWS Deep Learning AMIs (DLAMI) on two Amazon EC2 instances. Run the instances

• A
  17% (8)
• B
  8% (4)
• C
  71% (34)
• D
  4% (2)

Explanation

The requirements are near real-time, low-latency predictions with the ability to handle variable (unpredictable) request volumes. A SageMaker AI real-time endpoint with auto scaling satisfies both: it serves synchronous inference requests with millisecond-level latency, and auto scaling automatically adjusts the number of underlying instances up or down based on traffic load. Option A (batch transform) processes large datasets offline in batches - not real-time. Option B (API Gateway + S3) is not a valid model serving pattern; S3 cannot host a live inference endpoint. Option D (two fixed EC2 DLAMI instances) provides no auto scaling, so variable traffic spikes would either overload the instances or leave them idle.

No community discussion yet for this question.