Successful deployment of Machine Learning (ML) across the sciences calls for both a solid grasp of algorithms and a deep understanding of the application domain. This course brings those elements together in the context of empirical macroeconomic analysis. It pursues two objectives. The first is to give researchers and practitioners the practical skills needed to work with modern ML methods on macroeconomic data—a capability now in demand across academia, industry, and policy. The second is to cultivate the mindset and intuition required to adapt or design algorithms for the unique challenges posed by macroeconomic applications.

 We begin with core ML concepts and foundational ideas, then progress through classical and modern techniques—from regularized linear models to the architecture of large language models. Emphasis is placed not just on how these tools operate, but on the contexts in which they are most effective. The course devotes particular attention to recent innovations tailored to macroeconomics, including forecasting, latent state extraction, interpretability, density prediction, and other central tasks in applied time-series econometrics.Topics

 Topics

1.       Introduction to Machine Learning 

2.       Regularized Linear Models

3.       Kernel Methods

4.      Tree-Based Models

5.       Basic Neural Networks (NNs)

6.       Advanced Neural Networks Topics

7.       Uncertainty Quantification

8.       Interpretability

9.       Causality and Impulse Response Functions

10.   Macroeconomic Applications

By the end of the course, students will be able to:

·       apply core and modern ML methods to empirical data, including forecasting, latent-state extraction, and interpretability tools,

·       evaluate, implement, and adapt ML algorithms—ranging from regularized linear models to large-scale architectures,

·       critically assess empirical research that employs machine learning, with attention to model design, interpretability, and methodological suitability.

Attendance is mandatory.

The first part of the course consists of frontal lectures introducing key topics in ML for empirical (macroeconomic) analysis, while the end of the course features student presentations, discussion, and an exercise sheet illustrating the implementation and use of the methods covered in the lectures.

Attendance and proactive participation (20%), presentation of own research or replication of a relevant research paper (50%), exercise sheet (30%).

Please log in with your WU account to use all functionalities of read!t. For off-campus access to our licensed electronic resources, remember to activate your VPN connection connection. In case you encounter any technical problems or have questions regarding read!t, please feel free to contact the library at readinglists@wu.ac.at.

The course is suitable for students with prior training in macroeconomics and econometrics at the master’s level and with coding experience in Python, R, or Matlab.

By appointment.

Courses Material on Canvas (to be updated )