The Federal Open Market Committee (FOMC) sets the target for the federal funds rate, a critical tool influencing interest rates, inflation, and the broader economy. What if we could use large language models (LLMs) to anticipate their next decision?
In partnership with Bank of New York (BNY), our project developed a multi-agent simulation framework that leverages LLMs to simulate what’s happening behind closed doors in FOMC meetings and predict their outcomes. Simulated FOMC member agents analyze vast amounts of quantitative and qualitative macroeconomic data and conduct discussions before voting on a final decision for the federal funds target rate and its forward projections. The system replicates real-world decision-making dynamics by modeling the committee as AI agents with distinct perspectives. These discussions’ transparency illuminates the Fed’s complex reasoning for setting its target rate, allowing BNY to use this well-backtested system to manage risk and market expectations ahead of each FOMC meeting.
Mentor: David Ye
