Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Applying the propensity

Updated on August 4, 2022

Propensity is the likelihood of a customer responding positively to an action. To get the most accurate, granular results, configure Next-Best-Action to calculate propensity for each treatment. For example, if a customer is most likely to interact with a push notification, an action which has a push notification treatment is most suitable for that customer.

You can also calculate the propensity for each action, without taking treatments into account. This option is not recommended if you have treatments, but may be relevant if you did not create any treatments for your actions.

To ensure that only highly relevant actions and treatments are presented to customers, you can specify minimum propensity thresholds. Actions and treatments that do not meet these thresholds are not sent to customers.

Pega Customer Decision Hub
Before you begin: Define actions with corresponding treatments.
  1. In the Pega Customer Decision Hub portal, click Next-Best-ActionDesignerArbitration.
  2. In the Propensity section, ensure that the Apply propensity calculated for every treatment option is selected.
  3. Ensure that the toggle in the upper right corner of the Propensity section is set to on.
    If the toggle is inactive, Next-Best-Action no longer takes propensity into account when selecting the next best action for a customer.
  4. Optional: In the Predictions section, select the prediction used to determine the propensity for actions and treatments.
    By default, Pega Customer Decision Hub uses the built-in PredictActionPropensity and PredictTreatmentPropensity predictions. You can instead use different predictions that you created in Prediction Studio. For more information, see Predicting outcomes.
  5. Optional: In the Threshold section, specify one or more minimum propensity thresholds for the action or treatment.
    Actions and treatments that do not meet the propensity threshold are filtered out, so that customers receive only the most relevant messages.
  • Previous topic Prioritizing actions based on customer relevance and business priority
  • Next topic Applying the context weighting

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us