Modeling conversion rates and saving millions of dollars using Kaplan-Meier and gamma distributions

If you've ever wanted to do a better job of analyzing conversion rates, conversion rate changes over time, estimating lifetime value without needing to wait the entire lifetime, this post is for you. It's been going around Data Twitter this past week and it delivers. It doesn't just do a fantastic job of outlining problems and solutions, it actually delivers up a Python package, Convoys, that helps you do everything from the post.

This is one of the most common hard problems in modern analytics, and this is the best single post I've seen to take you from 0 to 60 on it. If you try Convoy I'd love to hear about your experiences.

Truly epic. Forward this to post your team.


Want to receive more content like this in your inbox?