A company has developed an ML model to predict real estate sale prices. The company wants to deploy the model to make predictions without managing servers or infrastructure. Which solution meets…

Question

Options

• ADeploy the model on an Amazon EC2 instance.
• BDeploy the model on an Amazon Elastic Kubernetes Service (Amazon EKS) cluster.
• CDeploy the model by using Amazon CloudFront with an Amazon S3 integration.
• DDeploy the model by using an Amazon SageMaker endpoint.

• B
  4% (1)
• C
  8% (2)
• D
  88% (22)

Explanation

Explanation

Amazon SageMaker endpoints provide a fully managed, serverless-like deployment option for ML models, meaning AWS handles all underlying server provisioning, scaling, and infrastructure management - exactly what the question requires. SageMaker is purpose-built for ML workflows, making it the ideal end-to-end solution for deploying, hosting, and running real-time predictions.

Why the distractors are wrong:

• Option A (EC2) requires you to manually provision, configure, and maintain virtual servers - the opposite of "no infrastructure management."
• Option B (Amazon EKS) involves managing Kubernetes clusters and container infrastructure, which still requires significant operational overhead.
• Option C (CloudFront + S3) is a content delivery/static storage solution with no capability to run or serve ML model inference.

Memory Tip

Think "SageMaker = ML without the heavy lifting." If an exam question mentions ML models + no server management, SageMaker endpoints are almost always the answer. A helpful acronym: SEME - SageMaker Endpoints Manage Everything (infrastructure-wise) so you don't have to.

No community discussion yet for this question.