Create an adaptive model to predict customer behavior. Refer to your Adaptive Model
rule in a strategy to use the propensity that the model returns. When you run the strategy,
adaptive models are created automatically for each unique combination of model identifiers in
the Adaptive Model rule instance.
- In the navigation pane of Prediction Studio, click Models.
- In the header of the Models work area,
Create adaptive model
dialog box, enter the model
and select the
section, enter the customer responses to
the behavior you want to predict:
- To select an available positive outcome for the model, place the cursor in the
empty field and, press Down Arrow, and click the outcome you want to use.
- To define a new positive outcome for the model, enter the outcome that you want to
section, enter which customer responses
represent the alternative outcome you want to predict:
- To select an available negative outcome for the model, place the cursor in the
empty field, press the Down Arrow key, and click the outcome you want to use.
- To define a new negative outcome for the model, enter the outcome you want to
- Optional: If online gradient boosting is enabled in your application, you can select the model
type in the Model type section by choosing from the following
- Different models per action - By default, different
adaptive models are created for every action.
- Common model for all actions - This experimental option
produces a single model for all actions by using the online gradient boosting machine
learning technique. In the early preview version available in Pega Platform version 8.1,
the model provides basic monitoring information.
- In the Context section, select the applicable class of the
model by performing the following actions:
- In the Apply to field, press Down Arrow, and select
application class of the model.
- In the new fields that appear, select a development branch and a ruleset.
Confirm the new adaptive model settings by clicking