The Hitchhiker’s Guide to Your Users. Personalization Through Causal ML

Did you ask yourself why some products have more conversion? Or why do some users select only a kind of product? In this talk, some of these questions are going to be treated and explained using causal inference. It will explain how to estimate the causal impact of intervention T on outcome Y for users with observed features X, without strong assumptions on the model form. Causal ML can be used to find the group of people that have a favorable response for a given metric such as engagement or sales. This is an example of campaign targeting optimization, but also it can be used to personalize the engagement with our clients. You can use it to estimate the effect for each customer for an optimal personalized recommendation system.