The SoFiE Summer School in Macro Finance 2026 is an intensive one-week program designed for graduate students, PhD candidates, early-career researchers, and professionals interested in the latest methodological advances in macroeconomics and finance.

This year’s edition focuses on how Artificial Intelligence and Machine Learning are transforming empirical macroeconomic analysis. Participants will explore cutting-edge methods and their applications to policy analysis, forecasting, and risk assessment, with direct relevance for academic research as well as for work in central banks, international institutions, and the private sector.

The program combines lectures by leading international scholars with discussions of frontier research and practical applications. Topics include tree-based methods, deep learning, and techniques for working with unstructured data, with particular emphasis on how these tools can be used to address contemporary macro-financial questions. The summer school offers a unique opportunity to develop new skills, engage with leading researchers, and deepen participants’ understanding of the tools shaping the future of macroeconomic analysis.

Summer School  
The course begins with an overview of the main AI and machine learning techniques increasingly used in economic analysis. It then examines a range of empirical applications relevant for macroeconomic analysis and policy.

In the first part, the course introduces tree-based methods and neural networks, with particular emphasis on deep learning. It also discusses how these techniques can handle data types beyond traditional numerical inputs, including text and other unstructured sources. For neural networks, the course presents different architectures and builds intuition about the types of problems for which each approach is best suited.

The second part of the course provides an in-depth review, supported by practical examples, of selected applications of AI in macroeconomic analysis. These include methods for capturing non-linearities in economic relationships, conducting risk analysis, and incorporating non-traditional data into forecasting models.

Overall, the course aims to equip participants with a solid understanding of modern AI and Machine Learning methods and the practical tools needed to develop their own applications in macroeconomic and financial analysis.

Workshop
Confirmed participants: Francesco Bianchi (JHU), Christian Brownless (LUISS), Stephen Hansen (University College London), Klodiana Istrevi (ECB), Adrian Peralta (IMF), Galina Potjagailo (Bank of England), Leif Anders Thorsrud (BI Oslo). 

The audience includes graduate students, academics, practitioners, and policymakers. Apply here. 

Applications should be submitted before 30/5/2026, early applications are strongly encouraged.

Applications must include a CV and a short motivation statement. Applicants wishing to present a paper (optional) should indicate this and attach a draft paper.

Acceptance decisions will be emailed by 30/5/2026 and may be communicated earlier for applications submitted before the deadline, in order to facilitate logistical arrangements.

Fees: €450 (PhD students), €900 (post-docs & faculty), €1350 (others), including VAT. 

A limited number of places are available for online participants at a 15% discounted rate.

Fees cover registration, lunches, and coffee breaks.

All accepted participants must be SoFiE members (or join before confirmation). Membership info: http://sofie.stern.nyu.edu/membership