Training adaptive models

Use the Call instruction with the DSMPublicAPI-ADM.pxUploadResponsesFromReport or Rule-Decision-AdaptiveModel.pyUploadResponsesFromReport activities to train adaptive models with data from a report definition on Interaction History fact records. The use of previous results allows for Adaptive Decision Manager to create models that are able to predict behavior.

1. Create an instance of the Activity rule by selecting Activity from the Technical category.

2. In the activity steps, use one of the following methods:

   • Recommended: Call DSMPublicAPI-ADM.pxUploadResponsesFromReport

   • Call Rule-Decision-AdaptiveModel.pyUploadResponsesFromReport

3. Click the arrow to the left of the Method field to expand the method and specify its parameters:

   • Name of the report definition

   • Class of the report definition

   • Page of class Embed-Decision-OutcomeColumnInfo

     This page needs to provide pyName as the outcome column in the report definition that defines the behavior and map these values to the possible outcomes from which the adaptive model rule learns.

   • Page of class Embed-Decision-AdaptiveModel-Key

     This page needs to provide the adaptive model parameters. Adaptive model parameters are values that point to the model in the channel (pyChannel and pyDirection), action dimension (pyIssue, pyGroup, and pyName) and class context (pyConfigurationAppliesTo and pyConfigurationName).

4. Click Save.

The report definition rule gathers the sample data. Only properties that are optimized for reporting when they have been created should be used in the report definition. The following example corresponds to a report definition that gathers work data. If the data is in an external data source, use the Connector & Metadata Wizard to create the necessary classes and rules.

Open topic with navigation