In this lab, you learn how to how to create real-time personalized movie recommendations with Amazon Personalize.

Amazon Personalize is a fully managed machine learning service that enables developers to build customized recommendation systems. Amazon Personalize makes it easy for developers to build applications capable of delivering a wide range of personalization experiences, including specific product recommendations, personalized product re-ranking, and customized direct marketing.
This lab walks you through the steps to create a personalized movie recommendation system, you can use these same steps to create other personalize content recommendations such as music or audio books.

Amazon Personalize does not require machine learning experience. You can build, train, and deploy a Amazon Personalize recommendation model (a solution version) with the AWS Management Console or programmatically by using the AWS SDK for Python. As a developer, you only need to do the following:

  • Format input data and upload the data into an Amazon S3 bucket, or send real-time event data.
  • Select a training recipe (algorithm) to use on the data.
  • Train a model (called a solution version in Amazon Personalize) using the recipe.
  • Deploy a campaign to make real-time recommendations or a batch processing job for batch recommendations.

AWS Experience: Intermediate

Time to complete: 2 hours

Cost to complete: This tutorial will cost you less than $1 (assuming all services are running for 2 hours)*

Technologies used:

• Active AWS Account**
• Browser: AWS recommends Chrome
• Amazon Personalize
• Amazon SageMaker
• AWS Identity and Access Management
• Amazon S3
• AWS SDK for Python

*This estimate assumes you follow the recommended configurations throughout the tutorial and terminate all resources within 2 hours.

**Accounts that have been created within the last 24 hours might not yet have access to the resources required for this project.