Hi,
I’ve created a lead scoring model for sales. The model performs well and passed every check. Now I have a list of probabilities to convert - The sales team doesn’t want to receive low probability leads nor do they want to spend their resources on leads that are near guaranteed to convert (both scenarios are a waste of time).
Is there a statistical method to segment these potential leads in a smart way?
One method that was discussed internally was running two models using the current logic for how we separate potential leads into sales / self-service and seeing if there is a difference between individual customers. However, this uses the inherent bias of the prior model…
Thoughts?