CONN 362 | Causal AI for Business Analytics

This course teaches students how to answer one of the most important questions in business analytics: what causes what, and what should be done about it. Students learn to distinguish causal effects from correlations and to design, analyze, and communicate evidence that supports high-quality business decisions. The course combines modern causal inference with Causal AI methods that use machine learning to estimate heterogeneous impacts and optimize targeting, while emphasizing identification, assumptions, and decision relevance. Students study randomized experiments (A/B testing) and a practical toolkit of observational and quasi-experimental designs used in industry and policy evaluation, including regression adjustment, matching and weighting with propensity scores, difference-in-differences and event studies, regression discontinuity, instrumental variables, and synthetic control. The course is hands-on and uses R throughout, culminating in professional deliverables such as experiment readouts and decision memos, plus monitoring plans and responsible-use considerations.