Domain use cases and custom recipes
Amazon Personalize provides different domain use cases and custom recipes for training models:
-
When you create a recommender in a Domain dataset group, you specify a use case. Amazon Personalize trains the models backing the recommender with the best configurations for the use case.
-
When you create a custom solution in a Custom dataset group or Domain dataset group, you specify a recipe and configure training parameters. When you create a solution version for the solution, Amazon Personalize trains the models backing the solution version based on the recipe and training configuration.