In this workshop you will learn how to implement a typical machine learning use case on the AWS platform end-to-end, in this case a recommender system.
You will start with implementing a prototype with Amazon Personalize and integrate it into our business application.
We will then train and serve our own recommendation machine learning model with Amazon SageMaker!
AWS Experience: Beginner
Time to Complete: 2-3 hours
- An AWS Account and Administrator-level access to it
Please be sure to terminate all of the resources created after this workshop to ensure that you are no longer charged.
Proceed to Lab 0 - Setting up your Amazon SageMaker Jupyter notebook instance
This workshop consists of following labs:
- Lab 0 - Setting up your Amazon SageMaker Jupyter notebook instance
- Lab 1 - Providing personalized movie recommendations using Amazon Personalize
- Lab 2 - Training and deploying a custom recommender model using Amazon SageMaker
Be sure to delete all of the resources created during the workshop in order to ensure that billing for the resources does not continue for longer than you intend. We recommend that you utilize the AWS Console to explore the resources you've created and delete them when you're ready.
For the two cases where you provisioned resources using AWS CloudFormation, you can remove those resources by simply running the following CLI command for each stack:
aws cloudformation delete-stack --stack-name STACK-NAME-HERETo remove all of the created resources, you can visit the following AWS Consoles, which contain resources you've created during the workshop:
Proceed to Lab 0 - Setting up your Amazon SageMaker Jupyter notebook instance