Date: 18 February 2026, Wednesday
Time: 10.30 – 11.30
Place: MA-330
“Monetary Policy Shocks: A New Hope —
Large Language Models and Central Bank Communication”
by
Ruben Fernandez Fuertes
Bocconi University
Abstract
I develop a multi-agent LLM framework that processes Federal Reserve communications to construct narrative monetary policy surprises. By analyzing Beige Books and Minutes released before each FOMC meeting, the system generates conditional expectations that yield less noisy surprises than market-based measures. These surprises produce theoretically consistent impulse responses where contractionary shocks generate persistent disinflationary effects, and enable profitable yield curve trading strategies that outperform alternatives. By directly extracting expectations rather than cleaning surprises ex post, this approach demonstrates how multi-agent LLMs can implement narrative identification at scale without contamination in high-frequency measure.
Bio
Rubén Fernández-Fuertes is a financial economist and former mathematician completing his PhD in Economics and Finance at Bocconi University. His research sits at the intersection of macro-finance, monetary policy, and large language models. His job market paper develops a multi-agent LLM framework that reads Federal Reserve communications to identify monetary policy shocks. His broader work spans term structure modeling, climate finance, and fiscal policy. He is a member of the European Parliament’s Monetary Policy Expert Panel and a former fellow at the Bank for International Settlements.