LECTURER
Martin Huber, Université de Fribourg
Course Type: elective
Credits: 5 ECTS
Grading and assignment of ECTS credits:
Participants have the opportunity to take an exam in order to obtain a grade. The format will be a take-home exam with empirical exercises using R to be submitted to martin.huber@unifr.ch until July 31st 2025.
SCHEDULE
Date of the Course: June 24 – 27, 2025
PREREQUISITES
All first year CDSE or equivalent courses.
COURSE CONTENT
This course introduces students to the concepts and purposes of predictive and causal machine learning, with a focus on practical application using real-world data. Methods covered include penalized regression (lasso, ridge), tree-based approaches (random forests, causal trees/forests), boosting, support vector machines, neural networks, and ensemble methods. Causal analysis topics include double machine learning, effect heterogeneity, optimal policy learning, and reinforcement learning. All methods are implemented using R and R Studio. Students will be expected to apply these tools and critically engage with their use in empirical research.
COMPETENCES ACQUIRED
Students become familiar with predictive and causal machine learning, understanding their goals, differences, and key methods. Using R and R Studio, they learn to apply these techniques to real data and critically assess their use in research.
FURTHER INFORMATION (LITERATURE AND RECOMMENDED TEXTBOOKS)
For predictive machine learning: G. James, D. Witten, T. Hastie, and R. Tibshirani (2021): An Introduction to Statistical Learning with Applications in R, Springer, New York. Freely available at: https://www.statlearning.com/
For causal machine learning: M. Huber (2023): Causal analysis - Impact evaluation and causal machine learning with applications in R, MIT Press, Cambridge. Freely readable at https://mitpress.ublish.com/ebook/causal-analysis-impact-evaluation-and-causal-machine-learning-with-applications-in-r-preview/12759/i