Causal Machine Learning for Growth: Loyalty Programs, LTV, and What to Do When You Can’t Experiment

Author(s): Torty Sivill

Originally published on Towards AI.

A hands-on guide to replacing A/B tests with counterfactual reasoning

It’s clear that causal inference is becoming increasingly critical. Companies that have relied heavily on experimentation are now facing situations where A/B testing is either infeasible, impractical or even counterproductive. They’re looking for alternative ways to derive causal insights from the data they already have.

The article discusses the challenges of relying solely on traditional A/B testing for assessing loyalty program impacts on customer lifetime value (LTV). It outlines the importance of causal inference as an alternative that leverages historical data to estimate outcomes without experimental setups. The author illustrates how to reconstruct counterfactual scenarios using causal graphs and discusses the limitations of causal discovery methods, calling for better tools and approaches to enhance causal inference accuracy in complex environments.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI