Applying the propensity
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.
- In the Pega Customer Decision Hub portal, click .
- In the Propensity section, ensure that the Apply propensity calculated for every treatment option is selected.
- 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.
- 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.
- 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