Hawkish or Dovish? That Is the Question: Agentic Retrieval of FED Monetary Policy Report

Ana Lorena Jiménez-Preciado, Mario Alejandro Durán-Saldivar, Salvador Cruz-Aké and Francisco Venegas-Martínez
Additional contact information
Ana Lorena Jiménez-Preciado: Escuela Superior de Economía, Instituto Politécnico Nacional, Red de Medio Ambiente. Av. Plan de Agua Prieta 66, Miguel Hidalgo, Mexico City 11350, Mexico
Mario Alejandro Durán-Saldivar: Escuela Superior de Economía, Instituto Politécnico Nacional, Red de Medio Ambiente. Av. Plan de Agua Prieta 66, Miguel Hidalgo, Mexico City 11350, Mexico
Salvador Cruz-Aké: Escuela Superior de Economía, Instituto Politécnico Nacional, Red de Medio Ambiente. Av. Plan de Agua Prieta 66, Miguel Hidalgo, Mexico City 11350, Mexico

Mathematics, 2025, vol. 13, issue 20, 1-23

Abstract: This paper develops a Natural Language Processing (NLP) pipeline to quantify the hawkish–dovish stance in the Federal Reserve’s semiannual Monetary Policy Reports (MPRs). The goal is to transform long-form central-bank text into reproducible stance scores and interpretable policy signals for research and monitoring. The corpus comprises 26 MPRs (26 February 2013 to 20 June 2025). PDFs are parsed and segmented and chunks are embedded, indexed with FAISS, retrieved via LangChain, and scored by GPT-4o on a continuous scale from −2 (dovish) to +2 (hawkish). Reliability is assessed with a four-dimension validation suite: (i) semantic consistency using cosine-similarity separation, (ii) numerical consistency against theory-implied correlation ranges (e.g., Taylor-rule logic), (iii) bootstrap stability of reported metrics, and (iv) content-quality diagnostics. Results show a predominant Neutral distribution (50.0%), with Dovish (26.9%) and Hawkish (23.1%). The average stance is near zero (≈0.019) with volatility σ ≈ 0.866, and the latest window exhibits a hawkish drift of ~+0.8 points. The Numerical Consistency Score is 0.800, and the integrated validation score is 0.796, indicating publication-grade robustness. We conclude that an embedding-based, agentic RAG approach with GPT-4o yields a scalable, auditable measure of FED communication; limitations include biannual frequency and prompt/model sensitivity, but the framework is suitable for policy tracking and empirical applications.

Keywords: monetary policy communication; hawkish–dovish classification; Federal Reserve; embeddings; FAISS; LangChain; retrieval-augmented generation; GPT-4o; policy uncertainty (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/20/3255/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/20/3255/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:20:p:3255-:d:1768899

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().