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…

Amazon SageMaker is a fully managed service designed to build, train, and deploy machine learning models at scale. When a model is deployed to a SageMaker endpoint, AWS handles all the underlying infrastructure management, including provisioning servers, patching, and auto-scaling. The user interacts with a secure, scalable API endpoint to get real-time predictions without any need to manage servers or infrastructure. This "serverless" approach for ML inference directly aligns with the company's requirements.

1. Amazon SageMaker Developer Guide: "When you host models

you deploy them to SageMaker endpoints. SageMaker performs the work of setting up and managing the resources for you. You send inference requests to the endpoint and receive predictions from your model."

Source: AWS Documentation

Amazon SageMaker Developer Guide

"Deploy a model".

2. AWS Documentation - What is Amazon EC2?: "Amazon Elastic Compute Cloud (Amazon EC2) is a web service that provides secure

resizable compute capacity in the cloud. It is designed to make web-scale cloud computing easier for developers. You have complete control of your computing resources..." This highlights the user's responsibility for management.

Source: AWS Documentation

Amazon EC2 User Guide for Linux Instances

"What is Amazon EC2?".

3. AWS Documentation - What is Amazon EKS?: "You are responsible for provisioning and managing worker nodes. [...] Amazon EKS helps you provide security for your Kubernetes clusters..." This clarifies that while EKS is managed

the underlying compute nodes are not

contradicting the serverless requirement.

Source: AWS Documentation

Amazon EKS User Guide

"What is Amazon EKS?".

4. University Courseware - MIT 6.S191: Introduction to Deep Learning: Course materials often distinguish between IaaS (like EC2) and managed ML platforms (like SageMaker)

emphasizing that managed platforms abstract away infrastructure management to accelerate deployment. SageMaker is presented as the solution for deploying models without managing servers.

Source: MIT OpenCourseWare

6.S191: Introduction to Deep Learning

Lecture on "Deep Learning in Practice". (Conceptual reference).