Companies such as e-commerce rely on Churn Modeling to identify customers that are likely to churn. Once identified, the company decides on a follow up action - a discount or a commercial - to hopefully retain those customers. Unfortunately, Churn models do not allow companies to assess whether or not their action is effective.
Uplift Modeling was designed to remedy this shortcoming by directly inferring the effect of an action on customers' retention.
As part of the New York User GroupEvent, @Jean-Yves(Technical Support Engineer at Dataiku) introduced the basics of Uplift Modeling, that is the requirements needed to train an uplift model, the types of models available (with a focus on S-learners) and the type of metrics used to evaluate the performance of such models.
Be sure to join the New York User Group to be informed of upcoming events and chat with fellow DSS users based in New York!
As you may know,Dataiku User Groupsare led by volunteer users who contribute their time and communication skills to enable fellow users to learn from each other. If you’d like to run this group, please fill out thisquick formand we’ll get back to you. Thanks for your interest!