FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction
This addresses the problem of monetary policy prediction for economists and policymakers, offering a transparent and accurate method, though it appears incremental as it builds on existing multi-agent and LLM techniques.
The paper tackled predicting the federal funds target rate by introducing FedSight AI, a multi-agent system using LLMs to simulate FOMC deliberations, and achieved 93.75% accuracy and 93.33% stability in 2023-2024 meetings, outperforming baselines like MiniFed and Ordinal RF.
The Federal Open Market Committee (FOMC) sets the federal funds rate, shaping monetary policy and the broader economy. We introduce \emph{FedSight AI}, a multi-agent framework that uses large language models (LLMs) to simulate FOMC deliberations and predict policy outcomes. Member agents analyze structured indicators and unstructured inputs such as the Beige Book, debate options, and vote, replicating committee reasoning. A Chain-of-Draft (CoD) extension further improves efficiency and accuracy by enforcing concise multistage reasoning. Evaluated at 2023-2024 meetings, FedSight CoD achieved accuracy of 93.75\% and stability of 93.33\%, outperforming baselines including MiniFed and Ordinal Random Forest (RF), while offering transparent reasoning aligned with real FOMC communications.