# Lead Scoring Not Wasting Everyone's Time

**URL:** <https://discourse.julialang.org/t/lead-scoring-not-wasting-everyones-time/94131>\
**Category:** Teaching & Outreach\
**Tags:** statistics, machine-learning\
**Created:** [February 6, 2023, 10:30am UTC](https://discourse.julialang.org/t/lead-scoring-not-wasting-everyones-time/94131 "2023-02-06T10:30:45Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Billpete002](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/billpete002/32/35091_2.png) [@Billpete002](https://discourse.julialang.org/u/Billpete002)\
**Post date:** [February 6, 2023, 10:30am UTC](https://discourse.julialang.org/t/lead-scoring-not-wasting-everyones-time/94131/1 "2023-02-06T10:30:45Z")

</div>

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?