Standard machine learning methods are powerful prediction tools, but they cannot be deployed for causal inference without putting additional structure on the estimation problem. This course provides a practical introduction to causal machine learning. We discuss the difference between predictive and causal machine learning and when which method should be applied. In particular, we focus on methods that allow to control for high-dimensional confounders (double machine learning), estimate heterogeneous effects of policy and business interventions (causal forest), and decision rules about the targeted implementation of these interventions (policy learning). We apply the methods to synthetic and real datasets in practical R sessions.

To attend the course / exercise, registration via e-learning platform OLAT is required. Registration is possible from 20 January – 3 February 2025. The students themselves are responsible for checking the creditability of the course to their course of study.

Direct link to OLAT course: https://lms.uzh.ch/url/RepositoryEntry/17670242421

Mandatory literature:

An Introduction to Statistical Learning with Applications in R (Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani). Free download: http://www-bcf.usc.edu/~gareth/ISL/

More literature references (mostly journal articles) will be provided during the lecture.