gtfintechlab/fomc_communication
收藏资源简介:
该数据集是最大的标记和注释的FOMC(联邦公开市场委员会)演讲、会议记录和新闻发布会记录的数据集,旨在理解货币政策如何影响金融市场。研究还开发了一个新的鹰派-鸽派分类任务,并在该数据集上对各种预训练语言模型进行了基准测试。使用表现最佳的模型(RoBERTa-large),构建了FOMC文件发布日的货币政策立场度量,并评估了其对国债市场、股票市场和宏观经济指标的影响。
This dataset is the largest labeled and annotated collection of Federal Open Market Committee (FOMC) speeches, meeting minutes, and press conference transcripts. It is designed to advance the understanding of how monetary policy impacts financial markets. The study further developed a novel hawk-dove classification task, and benchmarked various pre-trained language models on this dataset. Leveraging the best-performing model (RoBERTa-large), a monetary policy stance metric was constructed for the release dates of FOMC documents, and its impacts on treasury bond markets, stock markets, and macroeconomic indicators were evaluated.
数据集概述
许可证
- 许可证类型:CC BY-NC 4.0
任务类别
- 文本分类
语言
- 英语
标签
- 金融
数据规模
- 1K<n<10K
引用信息
- 论文标题:Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis
- 作者:Shah, Agam; Paturi, Suvan; Chava, Sudheer
- 会议:Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- 日期:2023年7月
- 地点:Toronto, Canada
- 出版商:Association for Computational Linguistics
- URL:https://aclanthology.org/2023.acl-long.368
- DOI:10.18653/v1/2023.acl-long.368
- 页码:6664--6679
- 摘要: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.
联系信息
- 联系人:Agam Shah
- 邮箱:ashah482[at]gatech[dot]edu
- GitHub:@shahagam4
- 网站:https://shahagam4.github.io/




