Managing recommenders
You don't have to manage the models backing your recommenders. Amazon Personalize automatically retrains them every 7 days. This is a full retraining that creates entirely new models based on the entirety of the data in your datasets. For Top picks for you and Recommended for you, Amazon Personalize updates the existing models every two hours to consider new items for recommendations with exploration. For more information, see Automatic updates.
Managing recommenders involves the following:
-
Stopping and starting recommenders – If you want to pause billing for an active recommender, you can stop the recommender and restart it later. For more information, see Stopping and starting a recommender.
-
Updating recommender configuration – You can update the columns the recommender uses in training and update the recommender's request capacity. For more information, see Updating a recommender.
-
Deleting a recommender – You can delete recommenders with the DeleteRecommender operation. Or you can delete a recommender from the recommender details page in the Amazon Personalize console.