aws_personalize_solution

account_id

Type: STRING

auto_ml_result

Type: STRUCT
Provider name: autoMLResult
Description: When performAutoML is true, specifies the best recipe found.

• best_recipe_arn
  Type: STRING
  Provider name: bestRecipeArn
  Description: The Amazon Resource Name (ARN) of the best recipe.
  

creation_date_time

Type: TIMESTAMP
Provider name: creationDateTime
Description: The creation date and time (in Unix time) of the solution.

dataset_group_arn

Type: STRING
Provider name: datasetGroupArn
Description: The Amazon Resource Name (ARN) of the dataset group that provides the training data.

event_type

Type: STRING
Provider name: eventType
Description: The event type (for example, ‘click’ or ’like’) that is used for training the model. If no eventType is provided, Amazon Personalize uses all interactions for training with equal weight regardless of type.

last_updated_date_time

Type: TIMESTAMP
Provider name: lastUpdatedDateTime
Description: The date and time (in Unix time) that the solution was last updated.

latest_solution_update

Type: STRUCT
Provider name: latestSolutionUpdate
Description: Provides a summary of the latest updates to the solution.

• creation_date_time
  Type: TIMESTAMP
  Provider name: creationDateTime
  Description: The date and time (in Unix format) that the solution update was created.
  
• failure_reason
  Type: STRING
  Provider name: failureReason
  Description: If a solution update fails, the reason behind the failure.
  
• last_updated_date_time
  Type: TIMESTAMP
  Provider name: lastUpdatedDateTime
  Description: The date and time (in Unix time) that the solution update was last updated.
  
• perform_auto_training
  Type: BOOLEAN
  Provider name: performAutoTraining
  Description: Whether the solution automatically creates solution versions.
  
• solution_update_config
  Type: STRUCT
  Provider name: solutionUpdateConfig
  Description: The configuration details of the solution.
  
  • auto_training_config
    Type: STRUCT
    Provider name: autoTrainingConfig
    
    • scheduling_expression
      Type: STRING
      Provider name: schedulingExpression
      Description: Specifies how often to automatically train new solution versions. Specify a rate expression in rate(value unit) format. For value, specify a number between 1 and 30. For unit, specify day or days. For example, to automatically create a new solution version every 5 days, specify rate(5 days). The default is every 7 days. For more information about auto training, see Creating and configuring a solution.
      
  • events_config
    Type: STRUCT
    Provider name: eventsConfig
    Description: Describes the configuration of an event, which includes a list of event parameters. You can specify up to 10 event parameters. Events are used in solution creation.
    
    • event_parameters_list
      Type: UNORDERED_LIST_STRUCT
      Provider name: eventParametersList
      Description: A list of event parameters, which includes event types and their event value thresholds and weights.
      
      • event_type
        Type: STRING
        Provider name: eventType
        Description: The name of the event type to be considered for solution creation.
        
      • event_value_threshold
        Type: DOUBLE
        Provider name: eventValueThreshold
        Description: The threshold of the event type. Only events with a value greater or equal to this threshold will be considered for solution creation.
        
      • weight
        Type: DOUBLE
        Provider name: weight
        Description: The weight of the event type. A higher weight means higher importance of the event type for the created solution.
        
• status
  Type: STRING
  Provider name: status
  Description: The status of the solution update. A solution update can be in one of the following states: CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED
  

latest_solution_version

Type: STRUCT
Provider name: latestSolutionVersion
Description: Describes the latest version of the solution, including the status and the ARN.

• creation_date_time
  Type: TIMESTAMP
  Provider name: creationDateTime
  Description: The date and time (in Unix time) that this version of a solution was created.
  
• failure_reason
  Type: STRING
  Provider name: failureReason
  Description: If a solution version fails, the reason behind the failure.
  
• last_updated_date_time
  Type: TIMESTAMP
  Provider name: lastUpdatedDateTime
  Description: The date and time (in Unix time) that the solution version was last updated.
  
• solution_version_arn
  Type: STRING
  Provider name: solutionVersionArn
  Description: The Amazon Resource Name (ARN) of the solution version.
  
• status
  Type: STRING
  Provider name: status
  Description: The status of the solution version. A solution version can be in one of the following states:
  • CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED
• training_mode
  Type: STRING
  Provider name: trainingMode
  Description: The scope of training to be performed when creating the solution version. A FULL training considers all of the data in your dataset group. An UPDATE processes only the data that has changed since the latest training. Only solution versions created with the User-Personalization recipe can use UPDATE.
  
• training_type
  Type: STRING
  Provider name: trainingType
  Description: Whether the solution version was created automatically or manually.
  

name

Type: STRING
Provider name: name
Description: The name of the solution.

perform_auto_ml

Type: BOOLEAN
Provider name: performAutoML
Description: We don’t recommend enabling automated machine learning. Instead, match your use case to the available Amazon Personalize recipes. For more information, see Determining your use case. When true, Amazon Personalize performs a search for the best USER_PERSONALIZATION recipe from the list specified in the solution configuration (recipeArn must not be specified). When false (the default), Amazon Personalize uses recipeArn for training.

perform_auto_training

Type: BOOLEAN
Provider name: performAutoTraining
Description: Specifies whether the solution automatically creates solution versions. The default is True and the solution automatically creates new solution versions every 7 days. For more information about auto training, see Creating and configuring a solution.

perform_hpo

Type: BOOLEAN
Provider name: performHPO
Description: Whether to perform hyperparameter optimization (HPO) on the chosen recipe. The default is false.

recipe_arn

Type: STRING
Provider name: recipeArn
Description: The ARN of the recipe used to create the solution. This is required when performAutoML is false.

solution_arn

Type: STRING
Provider name: solutionArn
Description: The ARN of the solution.

solution_config

Type: STRUCT
Provider name: solutionConfig
Description: Describes the configuration properties for the solution.

• algorithm_hyper_parameters
  Type: MAP_STRING_STRING
  Provider name: algorithmHyperParameters
  Description: Lists the algorithm hyperparameters and their values.
  
• auto_ml_config
  Type: STRUCT
  Provider name: autoMLConfig
  Description: The AutoMLConfig object containing a list of recipes to search when AutoML is performed.
  
  • metric_name
    Type: STRING
    Provider name: metricName
    Description: The metric to optimize.
    
  • recipe_list
    Type: UNORDERED_LIST_STRING
    Provider name: recipeList
    Description: The list of candidate recipes.
    
• auto_training_config
  Type: STRUCT
  Provider name: autoTrainingConfig
  Description: Specifies the automatic training configuration to use.
  
  • scheduling_expression
    Type: STRING
    Provider name: schedulingExpression
    Description: Specifies how often to automatically train new solution versions. Specify a rate expression in rate(value unit) format. For value, specify a number between 1 and 30. For unit, specify day or days. For example, to automatically create a new solution version every 5 days, specify rate(5 days). The default is every 7 days. For more information about auto training, see Creating and configuring a solution.
    
• event_value_threshold
  Type: STRING
  Provider name: eventValueThreshold
  Description: Only events with a value greater than or equal to this threshold are used for training a model.
  
• events_config
  Type: STRUCT
  Provider name: eventsConfig
  Description: Describes the configuration of an event, which includes a list of event parameters. You can specify up to 10 event parameters. Events are used in solution creation.
  
  • event_parameters_list
    Type: UNORDERED_LIST_STRUCT
    Provider name: eventParametersList
    Description: A list of event parameters, which includes event types and their event value thresholds and weights.
    
    • event_type
      Type: STRING
      Provider name: eventType
      Description: The name of the event type to be considered for solution creation.
      
    • event_value_threshold
      Type: DOUBLE
      Provider name: eventValueThreshold
      Description: The threshold of the event type. Only events with a value greater or equal to this threshold will be considered for solution creation.
      
    • weight
      Type: DOUBLE
      Provider name: weight
      Description: The weight of the event type. A higher weight means higher importance of the event type for the created solution.
      
• feature_transformation_parameters
  Type: MAP_STRING_STRING
  Provider name: featureTransformationParameters
  Description: Lists the feature transformation parameters.
  
• hpo_config
  Type: STRUCT
  Provider name: hpoConfig
  Description: Describes the properties for hyperparameter optimization (HPO).
  
  • algorithm_hyper_parameter_ranges
    Type: STRUCT
    Provider name: algorithmHyperParameterRanges
    Description: The hyperparameters and their allowable ranges.
    
    • categorical_hyper_parameter_ranges
      Type: UNORDERED_LIST_STRUCT
      Provider name: categoricalHyperParameterRanges
      Description: The categorical hyperparameters and their ranges.
      
      • name
        Type: STRING
        Provider name: name
        Description: The name of the hyperparameter.
        
      • values
        Type: UNORDERED_LIST_STRING
        Provider name: values
        Description: A list of the categories for the hyperparameter.
        
    • continuous_hyper_parameter_ranges
      Type: UNORDERED_LIST_STRUCT
      Provider name: continuousHyperParameterRanges
      Description: The continuous hyperparameters and their ranges.
      
      • max_value
        Type: DOUBLE
        Provider name: maxValue
        Description: The maximum allowable value for the hyperparameter.
        
      • min_value
        Type: DOUBLE
        Provider name: minValue
        Description: The minimum allowable value for the hyperparameter.
        
      • name
        Type: STRING
        Provider name: name
        Description: The name of the hyperparameter.
        
    • integer_hyper_parameter_ranges
      Type: UNORDERED_LIST_STRUCT
      Provider name: integerHyperParameterRanges
      Description: The integer-valued hyperparameters and their ranges.
      
      • max_value
        Type: INT32
        Provider name: maxValue
        Description: The maximum allowable value for the hyperparameter.
        
      • min_value
        Type: INT32
        Provider name: minValue
        Description: The minimum allowable value for the hyperparameter.
        
      • name
        Type: STRING
        Provider name: name
        Description: The name of the hyperparameter.
        
  • hpo_objective
    Type: STRUCT
    Provider name: hpoObjective
    Description: The metric to optimize during HPO. Amazon Personalize doesn’t support configuring the hpoObjective at this time.
    
    • metric_name
      Type: STRING
      Provider name: metricName
      Description: The name of the metric.
      
    • metric_regex
      Type: STRING
      Provider name: metricRegex
      Description: A regular expression for finding the metric in the training job logs.
      
    • type
      Type: STRING
      Provider name: type
      Description: The type of the metric. Valid values are Maximize and Minimize.
      
  • hpo_resource_config
    Type: STRUCT
    Provider name: hpoResourceConfig
    Description: Describes the resource configuration for HPO.
    
    • max_number_of_training_jobs
      Type: STRING
      Provider name: maxNumberOfTrainingJobs
      Description: The maximum number of training jobs when you create a solution version. The maximum value for maxNumberOfTrainingJobs is 40.
      
    • max_parallel_training_jobs
      Type: STRING
      Provider name: maxParallelTrainingJobs
      Description: The maximum number of parallel training jobs when you create a solution version. The maximum value for maxParallelTrainingJobs is 10.
      
• optimization_objective
  Type: STRUCT
  Provider name: optimizationObjective
  Description: Describes the additional objective for the solution, such as maximizing streaming minutes or increasing revenue. For more information see Optimizing a solution.
  
  • item_attribute
    Type: STRING
    Provider name: itemAttribute
    Description: The numerical metadata column in an Items dataset related to the optimization objective. For example, VIDEO_LENGTH (to maximize streaming minutes), or PRICE (to maximize revenue).
    
  • objective_sensitivity
    Type: STRING
    Provider name: objectiveSensitivity
    Description: Specifies how Amazon Personalize balances the importance of your optimization objective versus relevance.
    
• training_data_config
  Type: STRUCT
  Provider name: trainingDataConfig
  Description: Specifies the training data configuration to use when creating a custom solution version (trained model).
  
  • excluded_dataset_columns
    Type: STRING
    Provider name: excludedDatasetColumns
    Description: Specifies the columns to exclude from training. Each key is a dataset type, and each value is a list of columns. Exclude columns to control what data Amazon Personalize uses to generate recommendations. For example, you might have a column that you want to use only to filter recommendations. You can exclude this column from training and Amazon Personalize considers it only when filtering.
    

status

Type: STRING
Provider name: status
Description: The status of the solution. A solution can be in one of the following states:

• CREATE PENDING > CREATE IN_PROGRESS > ACTIVE -or- CREATE FAILED
• DELETE PENDING > DELETE IN_PROGRESS

tags

Type: UNORDERED_LIST_STRING