Dears

We are working to design and deploy ADM on the NBA portal of our client. The client's expectations are that the NBA ADM engine would not only drive success rates but prioritize value/revenue uplift over success rate. I read somewhere that one of the companies in the US is using the delayed learning in PEGA to embed the value uplift aspect into the model learning.

Concept:

1. Store the  decision data for a certain period (example 10 days)

2. Even if the customers accept on 2nd day, it is parked and not fed into the ADM

3. Define the outcome after 10 days basis the below condition: If response='Accept' and Rev After 10 days  > Rev before 10 days  then 'POSITIVE' else 'NEGATIVE'

I need your valuable input on the same. How exactly can we apply a similar concept in our design.

Hoping for a solution.

Thanks

Vaibhav

***Edited by Moderator Marissa to update Pega Academy to General; Content Type from Discussion to Question***