Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis

Agam Shah, Suvan Paturi, Sudheer Chava
5/13/2023
cs.CLq-fin.CP

No official code found. Best implementation: gtfintechlab/fomc-hawkish-dovish (67 stars, last commit 2024-12-17).

Abstract

Monetary policy pronouncements by Federal Open Market Committee (FOMC) are a major driver of financial market returns. We construct the largest tokenized and annotated dataset of FOMC speeches, meeting minutes, and press conference transcripts in order to understand how monetary policy influences financial markets. In this study, we develop a novel task of hawkish-dovish classification and benchmark various pre-trained language models on the proposed dataset. Using the best-performing model (RoBERTa-large), we construct a measure of monetary policy stance for the FOMC document release days. To evaluate the constructed measure, we study its impact on the treasury market, stock market, and macroeconomic indicators. Our dataset, models, and code are publicly available on Huggingface and GitHub under CC BY-NC 4.0 license.

View on arXivView PDF

Code Implementations(1)

gtfintechlab/fomc-hawkish-dovishCommunity100%

Codebase for FOMC-NLP, accepted at ACL 2023 (main)

6722HTML, PythonFeb 7, 20221 years agoNOASSERTION

Similar Papers

FMPAF: How Do Fed Chairs Affect the Financial Market? A Fine-grained Monetary Policy Analysis Framework on Their Language

82% match2024

Modeling Hawkish-Dovish Latent Beliefs in Multi-Agent Debate-Based LLMs for Monetary Policy Decision Classification

81% match2025

Analysis of the Fed's communication by using textual entailment model of Zero-Shot classification

80% match2023

Analyzing FOMC Minutes: Accuracy and Constraints of Language Models

80% match2023

Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications Globally

80% match1 repo222025

Transforming Sentiment Analysis in the Financial Domain with ChatGPT

80% match1 repo212023

Cite this paper

@article{shah2023trillion,
  title  = {Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis},
  author = {Agam Shah and Suvan Paturi and Sudheer Chava},
  year   = {2023},
  eprint = {2305.07972},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.07972v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.07972.svg)](https://codeofpaper.com/paper/2305.07972)

Discussion