用AI模拟美联储议息决策，预测利率走向
FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction
- 构建多智能体系统，模仿美联储委员分析数据与辩论投票
- 2023-2024年预测准确率达93.75%，高于基准模型
- 推理过程透明，符合真实货币政策沟通风格
美联储公开市场委员会（FOMC）决定联邦基金利率，影响货币政策与整体经济。我们提出FedSight AI，一种基于大语言模型（LLMs）的多智能体框架，模拟FOMC讨论过程并预测政策结果。成员智能体分析结构化指标与非结构化输入（如《褐皮书》），进行观点辩论与投票，复现委员会决策逻辑。引入链式草稿（Chain-of-Draft, CoD）机制，强化多阶段简洁推理，提升效率与准确性。在2023–2024年会议评估中，FedSight CoD达到93.75%的准确率与93.33%的稳定性，优于MiniFed与序数随机森林（Ordinal RF）等基线模型，且推理过程透明，与真实FOMC沟通一致。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。