A company has an ML model that predicts real estate sale prices and wants to serve predictions without managing servers or infrastructure. Which deployment option meets this requirement?
Choose an answer
Tap an option to check your answer.
Correct answer: Deploy the model using an Amazon SageMaker endpoint..
Why this is the answer
Deploying the model using an Amazon SageMaker endpoint is the correct choice because SageMaker endpoints are fully managed services designed for real-time inference, eliminating the need to provision or manage servers. This aligns perfectly with the requirement of serving predictions without managing infrastructure. Hosting on an Amazon EC2 instance would require manual server management and scaling. Deploying to an Amazon Elastic Kubernetes Service (EKS) cluster also involves managing Kubernetes infrastructure. Serving through Amazon CloudFront integrated with Amazon S3 is primarily for content delivery, not for real-time model inference that requires compute.
Pass your exam — without the endless answer hunt
Get every verified question and explanation for this exam in one place, and save hours of prep. 1,000+ certifications · 20+ languages · free to start.
Pass your exam faster → No card needed