Datasets
The following topics provide detailed information on Amazon Personalize datasets. Each type of dataset has different data requirements. For both Domain dataset groups and Custom dataset groups, your interactions data must have the following before training:
-
At minimum 1000 item interactions records from users interacting with items in your catalog. These interactions can be from bulk imports, or streamed events, or both.
-
At minimum 25 unique user IDs with at least two item interactions for each.
For quality recommendations, we recommend that you have at minimum 50,000 item interactions from at least 1,000 users with two or more item interactions each.
If you create a Domain dataset group, each dataset has additional requirements depending on domain. If you aren't sure what type of data you need, we recommend creating a Domain dataset group and using the default schemas for your domain as a guide. For more information about dataset and schema requirements see Schemas.
