Real-time action recommendations in Amazon Personalize

If you use a PERSONALIZED_ACTIONS recipe, you can get action recommendations from your campaign in real time. You can get action recommendations with the Amazon Personalize console, AWS Command Line Interface (AWS CLI), or AWS SDKs.

How action recommendation scoring works

With the Next-Best-Action recipe, Amazon Personalize generates scores for actions based on the likelihood that the user will interact with the action. Scores can be between 0 – 1.0. The closer to 1.0, the more likely it is that the user will interact with the action.

If you haven't imported any action interaction data, all recommended actions will have a score of 0.0. If Amazon Personalize recommends an action as part of exploration, the item will have a score of 0.0. Amazon Personalize uses exploration to recommend actions without action interaction data. For more information about exploration, see Exploration.

Getting action recommendations (console)

To get action recommendations with the Amazon Personalize console, you provide the request information on the details page of your custom campaign.

Getting action recommendations (AWS CLI)

Use the following code to get action recommendations from a campaign. Specify the ID of the user that you want to get recommendations for and the Amazon Resource Name (ARN) of your campaign.

To change the number of recommended actions, change the value for numResults. The default is 5 actions. The maximum is 100 actions.

To filter actions recommendations by custom criteria, you can create a filter and apply it to the get-action-recommendations operation. For more information, see Filtering recommendations and user segments.

If you recorded events for a user before they logged in (an anonymous user), you can get recommendations for this user by providing the sessionId from those events as if it is their userId. For more information about recording events for anonymous users, see Recording events for anonymous users.

aws personalize-runtime get-action-recommendations \
--campaign-arn campaign arn \
--user-id User ID \
--num-results 10

Getting action recommendations (AWS SDKs)

The following code shows how to get Amazon Personalize recommendations for a user from a campaign. Specify the ID of the user you want to get recommendations for, and the Amazon Resource Name (ARN) of your campaign.

To change the number of recommended actions, change the value for numResults. The default is 5 actions. The maximum is 100 actions.

To filter actions recommendations by custom criteria, you can create a filter and apply it to the GetActionRecommendations API request. For more information, see Filtering recommendations and user segments.

If you recorded events for a user before they logged in (an anonymous user), you can get recommendations for this user by providing the sessionId from those events as if it is their userId. For more information about recording events for anonymous users, see Recording events for anonymous users.

import boto3

personalizeRt = boto3.client('personalize-runtime')

response = personalizeRt.get_action_recommendations(
    campaignArn = 'Campaign ARN',
    userId = 'User ID',
    numResults = 10
)

print("Recommended actions")
for item in response['actionList']:
    print (item['actionId'])