5.2.4.3 Behavioral Model Feature Contribution for Non-Alerted Entities

• This pre-seeded batch is available in all workspaces (Production and Sandboxes).

  Note:

  This batch has to be executed in the Production workspace.
• This batch shows the feature contributions for non-alerted entities.
• The batch is designed to run on ad-hoc basis when there is a need to view feature contribution for historical entities.

  Figure 5-40 Feature Contribution for Non-Alerted Entities

  
  

  
  Description of "Figure 5-40 Feature Contribution for Non-Alerted Entities"

  
  

Batch and Task Parameters

• The batch contains a single task named SM_Feature_Contribution_Non-Alerted.
• Objective folder for Feature_Contribution_Non_alerted: Home / Modeling / Pipelines / ML4AML / Scenario Model / Batch / Feature Contribution Non Alerted
• Model: Retain the default settings.

  Note:

  • For a fresh installation, do not modify any parameters except the Optional Parameters.
  • For upgrade, see the How to Execute Monthly Model Validation with the Batch Framework section.
• Optional Parameters:
  • model_group_name: Name of the model group for which the model has been trained. For example, LOB1.
  • model_name: Name of the model that has been trained. For example, RMF.
  • focus: Name of the entity type or segment. For example, CUSTOMER.
  • entity_id: List of entity IDs (separated by tildes ~) for which the feature contributions are to be retrieved. If no entities are specified, the top 10 entities with the highest event scores will be selected by default. For example, CUST_101~CUST_102.

    Example for Optional Parameters: model_group_name=LOB1,model_name=RMF,focus=CUSTOMER,entity_id=CUST101~CUST102

• Edit Task Parameters and Save.