This dataset contains the textual data of Federal Reserve FOMC meetings statements and minutes.

Column description

• Date - Date of the FOMC meeting.
• Release Date - Release date of the statement/minutes. Note that minutes are usually released with a ~3 week lag from the meeting date.
• Type - Communication type, either a statement or minutes.
• Text - The text content of each communication release.

Update schedule

This dataset is updated on a weekly basis with new data sourced from the Federal Reserve website.

United States - FOMC Summary of Economic Projections for the Growth Rate of Real Gross Domestic Product, Range, Midpoint was 1.55000 Fourth Qtr. to Fourth Qtr. % Chg. in January of 2027, according to the United States Federal Reserve. Historically, United States - FOMC Summary of Economic Projections for the Growth Rate of Real Gross Domestic Product, Range, Midpoint reached a record high of 5.55000 in January of 2021 and a record low of -2.15000 in January of 2020. Trading Economics provides the current actual value, an historical data chart and related indicators for United States - FOMC Summary of Economic Projections for the Growth Rate of Real Gross Domestic Product, Range, Midpoint - last updated from the United States Federal Reserve on July of 2025.

Textual Time Series Dataset for finetuning / pretraining. Json version of original dataset. Original Dataset : https://www.kaggle.com/datasets/vladtasca/fomc-meeting-statements-and-minutes

Dataset adapted from original work by Shah et al.

  About Dataset

The dataset is a collection of sentences from FOMC speeches, meeting minutes and press releases (see corresponding paper). A subset of the data has been manually annotated as hawkish, dovish, or neutral.

  Label mapping

LABEL 2: Neutral LABEL 1: Hawkish LABEL 0: Dovish

  Counterfactual generation split

Additionally, for counterfactual generation tasks, we add a custom split with target classes in… See the full description on the dataset page: https://huggingface.co/datasets/TextCEsInFinance/fomc-communication-counterfactual.

Dataset Summary

For dataset summary, please refer to https://huggingface.co/datasets/gtfintechlab/federal_reserve_system

  Additional Information

This dataset is annotated across three different tasks: Stance Detection, Temporal Classification, and Uncertainty Estimation. The tasks have four, two, and two unique labels, respectively. This dataset contains 1,000 sentences taken from the meeting minutes of the Federal Reserve System.

  Label Interpretation… See the full description on the dataset page: https://huggingface.co/datasets/gtfintechlab/federal_reserve_system.

The narrative approach to macroeconomic identification uses qualitative sources, such as newspapers or government records, to provide information that can help establish causal relationships. This paper discusses the requirements for rigorous narrative analysis using fresh research on the impact of monetary policy as the focal application. We read the historical minutes and transcripts of Federal Reserve policymaking meetings to identify significant contractionary and expansionary changes in monetary policy not taken in response to current or prospective developments in real activity for the period 1946 to 2016. We find that such monetary shocks have large and significant effects on unemployment, output, and inflation in the expected directions. Analysis of available policy records suggests that a contractionary monetary shock likely occurred in 2022. Based on the empirical estimates of the effect of previous shocks, one would expect substantial negative impacts on real GDP and inflation in 2023 and 2024.

Label Interpretation

LABEL_2: NeutralLABEL_1: HawkishLABEL_0: Dovish

  Citation and Contact Information





  Cite

Please cite our paper if you use any code, data, or models. @inproceedings{shah-etal-2023-trillion, title = "Trillion Dollar Words: A New Financial Dataset, Task {&} Market Analysis", author = "Shah, Agam and Paturi, Suvan and Chava, Sudheer", booktitle = "Proceedings of the 61st Annual Meeting of the Association for… See the full description on the dataset page: https://huggingface.co/datasets/gtfintechlab/fomc_communication.