Getting started
The following sections help you get started using Amazon Personalize with the Amazon Personalize console, Amazon CLI, and Amazon SDKs. The tutorials use historical data that consists of 100,000 movie ratings on 9,700 movies from 600 users.
To simplify tutorials:
-
We use a small dataset. This might negatively impact any metrics generated by resources. The tutorials serve as an introduction to the Amazon Personalize workflow and won't necessarily generate the highest performing models.
We create only an Item interactions dataset, and rely on the fact that a user saw a movie and not on what they rated the movie. This simplifies the preparation of the training data.
-
We don't record live user interaction events. For information on capturing user events, see Recording events.
You can choose to get started with a Domain dataset group or a Custom dataset group:
-
Domain dataset groups provide resources that are optimized for different use cases based on your domain. To get started creating a Domain dataset group, complete the Getting started prerequisites and then complete the tutorial in Getting started with a Domain dataset group.
-
Custom dataset groups allow you to create and configure only custom resources. To get started providing personalized movie recommendations for your users with a custom resources and the User-Personalization recipe, complete the Getting started prerequisites and then start the tutorials in Getting started with a Custom dataset group.
When you finish the getting started exercise, to avoid incurring unnecessary charges, follow the steps in Cleaning up resources to delete the resources you created.