FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915683647881216 |
|---|---|
| author | Hou, Yuhan Rao, Tianji Tan, Jeremy Viton, Adler Zhang, Xiyue Ye, David Kodi, Abhishek Dulam, Sanjana Paul, Aditya Feng, Yikai |
| author_facet | Hou, Yuhan Rao, Tianji Tan, Jeremy Viton, Adler Zhang, Xiyue Ye, David Kodi, Abhishek Dulam, Sanjana Paul, Aditya Feng, Yikai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction Hou, Yuhan Rao, Tianji Tan, Jeremy Viton, Adler Zhang, Xiyue Ye, David Kodi, Abhishek Dulam, Sanjana Paul, Aditya Feng, Yikai General Finance Artificial Intelligence 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. |
| title | FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction |
| topic | General Finance Artificial Intelligence |
| url | https://arxiv.org/abs/2512.15728 |