:doc:`PersonalizeRuntime <../../personalize-runtime>` / Client / get_action_recommendations

**************************
get_action_recommendations
**************************



.. py:method:: PersonalizeRuntime.Client.get_action_recommendations(**kwargs)

  

  Returns a list of recommended actions in sorted in descending order by prediction score. Use the ``GetActionRecommendations`` API if you have a custom campaign that deploys a solution version trained with a PERSONALIZED_ACTIONS recipe.

   

  For more information about PERSONALIZED_ACTIONS recipes, see `PERSONALIZED_ACTIONS recipes <https://docs.aws.amazon.com/personalize/latest/dg/nexts-best-action-recipes.html>`__. For more information about getting action recommendations, see `Getting action recommendations <https://docs.aws.amazon.com/personalize/latest/dg/get-action-recommendations.html>`__.

  

  See also: `AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/personalize-runtime-2018-05-22/GetActionRecommendations>`_  


  **Request Syntax**
  ::

    response = client.get_action_recommendations(
        campaignArn='string',
        userId='string',
        numResults=123,
        filterArn='string',
        filterValues={
            'string': 'string'
        }
    )
    
  :type campaignArn: string
  :param campaignArn: 

    The Amazon Resource Name (ARN) of the campaign to use for getting action recommendations. This campaign must deploy a solution version trained with a PERSONALIZED_ACTIONS recipe.

    

  
  :type userId: string
  :param userId: 

    The user ID of the user to provide action recommendations for.

    

  
  :type numResults: integer
  :param numResults: 

    The number of results to return. The default is 5. The maximum is 100.

    

  
  :type filterArn: string
  :param filterArn: 

    The ARN of the filter to apply to the returned recommendations. For more information, see `Filtering Recommendations <https://docs.aws.amazon.com/personalize/latest/dg/filter.html>`__.

     

    When using this parameter, be sure the filter resource is ``ACTIVE``.

    

  
  :type filterValues: dict
  :param filterValues: 

    The values to use when filtering recommendations. For each placeholder parameter in your filter expression, provide the parameter name (in matching case) as a key and the filter value(s) as the corresponding value. Separate multiple values for one parameter with a comma.

     

    For filter expressions that use an ``INCLUDE`` element to include actions, you must provide values for all parameters that are defined in the expression. For filters with expressions that use an ``EXCLUDE`` element to exclude actions, you can omit the ``filter-values``. In this case, Amazon Personalize doesn't use that portion of the expression to filter recommendations.

     

    For more information, see `Filtering recommendations and user segments <https://docs.aws.amazon.com/personalize/latest/dg/filter.html>`__.

    

  
    - *(string) --* 

    
      - *(string) --* 

      


  
  :rtype: dict
  :returns: 
    
    **Response Syntax**

    
    ::

      {
          'actionList': [
              {
                  'actionId': 'string',
                  'score': 123.0
              },
          ],
          'recommendationId': 'string'
      }
      
    **Response Structure**

    

    - *(dict) --* 
      

      - **actionList** *(list) --* 

        A list of action recommendations sorted in descending order by prediction score. There can be a maximum of 100 actions in the list. For information about action scores, see `How action recommendation scoring works <https://docs.aws.amazon.com/personalize/latest/dg/how-action-recommendation-scoring-works.html>`__.

        
        

        - *(dict) --* 

          An object that identifies an action.

           

          The API returns a list of ``PredictedAction``s.

          
          

          - **actionId** *(string) --* 

            The ID of the recommended action.

            
          

          - **score** *(float) --* 

            The score of the recommended action. For information about action scores, see `How action recommendation scoring works <https://docs.aws.amazon.com/personalize/latest/dg/how-action-recommendation-scoring-works.html>`__.

            
      
    
      

      - **recommendationId** *(string) --* 

        The ID of the recommendation.

        
  
  **Exceptions**
  
  *   :py:class:`PersonalizeRuntime.Client.exceptions.InvalidInputException`

  
  *   :py:class:`PersonalizeRuntime.Client.exceptions.ResourceNotFoundException`

  