ORIE 5751 - Applied Causal Inference using Machine Learning

(crosslisted) CS 5726

Spring. 3 credits. Student option grading.

Prerequisite: ORIE 5750 or CS 5785 and working knowledge of calculus, probability, and linear algebra as well as a modern scripting language such as Python. Enrollment limited to: Cornell Tech students. Students are expected to have taken a first course in machine learning and have working knowledge of calculus, probability, and linear algebra as well as a modern scripting language such as Python. Offered in New York City at Cornell Tech.

N. Kallus.

Provides an applied treatment of modern causal inference using machine learning to handle high-dimensionality and nonparametric estimation. Formulates key causal questions in the languages of structural equation modeling and potential outcomes. Presents methods for estimating and constructing confidence intervals on causal and structural parameters using machine learning, including de-biased machine learning, and for learning how to predict heterogeneous treatment effects. Introduces tools from machine learning and deep learning developed for prediction purposes and discusses how to adapt them to causal inference. Emphasizes the applied and practical perspectives with real-world-data examples and assignments. Requires basic knowledge of statistics and machine learning and programming experience in R or Python.