Client wants to choose between propensity provided by Pega adaptive model Vs propensity score from an external predictive model(stored in a table in Pega) based on some specific condition.
We were thinking of implementing this via a switch component in an extension strategy (may be AI Models Ext strategy ext component). Can you please let us know -
Is there is any OOTB extension strategy component where this can be achieved ?
As this is taken care in the arbitration component of Pega, can you please let us know the best possible way to implement this functionality.
@sumanpyne Hi Suman, we would always recommend to use the propensities from the adaptive model. If any external scores are available they can be leveraged as predictors to the adaptive model. In this way the different propensities are also scaled in the same way and can be compared against each other without bias in arbitration. Note also that the granularity of treatments is usually much higher than any available offline scores.
If you choose to extend using the AIModelsExt strategy, take care that there are steps such as Thompson sampling and maturity capping that happen after that,