FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction

2025-12-05

AI Summary

This paper addresses the critical monetary policy problem of forecasting the Federal Funds Target Rate. Methodologically, it proposes an interpretable prediction framework based on a multi-agent system that simulates heterogeneous FOMC members’ decision-making processes. The framework jointly models structured economic indicators and unstructured textual data (e.g., the Beige Book) and introduces Chain-of-Draft (CoD), a novel multi-step refinement reasoning mechanism enabling inter-agent debate, consensus formation, and voting-based decision-making—thereby ensuring transparency and alignment with actual FOMC communication logic. Empirical evaluation on 2023–2024 FOMC meetings yields 93.75% prediction accuracy and 93.33% stability, significantly outperforming baselines including MiniFed and ordinal random forests. The core contributions are: (1) the first proposal of the CoD reasoning paradigm; and (2) the unified integration of heterogeneous multimodal data modeling with interpretable, process-aware policy decision-making.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

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.

Problem

• Predicts federal funds rate using multi-agent LLM simulations
• Simulates FOMC deliberations with structured and unstructured data
• Improves prediction accuracy and transparency over baseline models

Innovation

• Multi-agent LLM system simulates FOMC deliberations
• Chain-of-Draft extension enforces concise multistage reasoning
• Analyzes structured and unstructured inputs for rate prediction