Climbing the causal ladder for fun and profit
In this talk, we will explore Judea Pearl’s causal ladder (association, intervention, and counterfactuals) through the lens of a simple demand forecasting model. Using real-world business scenarios, I will demonstrate how to move beyond correlation-based predictions to more actionable decisions using PyMC’s causal inference tools. Attendees will learn how to make forecasts for natural business conditions, simulate the effects of strategic changes (like increased advertising spend), and evaluate the causal impact of past price promotion with retrodictive causal inference.
Target audience: Data scientists, machine learning engineers, and business analysts looking to improve their decision-making using causal inference.