Step 4: Getting recommendations
Depending on your resources, you can get recommendations in real time or with a batch workflow.
-
With custom resources, you can get real-time recommendations or batch recommendations. For real-time recommendations, you must create a custom campaign before you get recommendations. For batch recommendations, you don't need to create a campaign.
-
With recommenders in a Domain dataset group, you can get only real-time recommendations.
The following topics explain how and when to use each recommendation type.
Topics
Recommendation scores
With custom solutions created with the User-Personalization, Personalized-Ranking, and PERSONALIZED_ACTIONS recipes, Amazon Personalize includes a score for each item in recommendations. These scores represent the relative certainty that Amazon Personalize has about which item or action the user will select next. Higher scores represent greater certainty.
-
For information about scores for User-Personalization, see How User-Personalization recommendation scoring works (custom resources).
-
For information about scores for PERSONALIZED_ACTIONS recipes, see How action recommendation scoring works.
-
For information on scores for Personalized-Ranking recommendations, see How personalized ranking scoring works.
For batch inference jobs, item scores are calculated just as described in How User-Personalization recommendation scoring works (custom resources) and How personalized ranking scoring works. You can view scores in the batch inference job's output JSON file.