CEMLA Course: Modern Machine Learning for Macroeconomic Forecasting

Foundation models and automated ML have revolutionized forecasting workflows. Models like Chronos-2 enable zero-shot forecasting on new datasets without training, while TabPFN achieves state-of-the-art performance on small tabular datasets in seconds. Central banks can leverage these advances to improve forecast accuracy, reduce modeling time, and better quantify uncertainty for policy decisions.

This intensive course bridges classical econometric forecasting with modern machine learning approaches, focusing on practical applications for central banking. The course emphasizes understanding the funda mental tradeoffs between classical and ML methods, hands-on implementation with state-of-the-art tools (AutoGluon, Chronos-2, TabPFN), and production deployment considerations.