Course Program

Purpose of Lectures

The Summer School lecture series is designed to equip PhD students in economics, finance and related fields with cutting-edge computational tools transforming modern economic research. By integrating applied mathematics, machine learning, computational science, and computational economics, these lectures will provide a deep dive into solving and estimating dynamic stochastic economic models while addressing the challenges of parametric uncertainty quantification.

Two powerful machine learning methods are at the program's core: Deep Neural Networks and Gaussian Processes. These techniques have gained prominence for their ability to approximate complex functional relationships, enhance predictive accuracy, and model economic dynamics in ways previously unattainable. Their practical applications will be demonstrated through case studies in macroeconomics and climate change economics, showcasing how these methods can tackle real-world economic and financial problems.

What sets these lectures apart is their interactive, workshop-style format. Participants will not only engage in theoretical discussions but will also have the opportunity to apply their knowledge through hands-on coding exercises. With practical examples provided in Python and deployed on cloud computing infrastructure, students will gain firsthand experience in implementing machine learning solutions on scalable platforms. All hands-on components of the summer courses will be powered by Nuvolos, a cloud-based teaching platform enabling reproducible, scalable, and frictionless computational environments.

By the end of the series, participants will have developed a robust skill set in computational economics and machine learning, empowering them to push the boundaries of research in dynamic stochastic modeling. Whether you're exploring economic forecasting, policy simulations, or financial risk assessment, this summer school provides the essential tools to drive innovation in economic analysis.

Registration Deadline: 30th April 2025

The schedule