Content-Based Metric on Monetary Policy Uncertainty by Using Large Language Models

17 Pages Posted: 10 Dec 2024

See all articles by Arata Ito

Arata Ito

Research Institute of Economy, Trade and Industry (RIETI)

Masahiro Sato

Tohoku University - Graduate School of International Cultural Studies

Rui Ota

Meiji University - School of Commerce

Abstract

Policy uncertainty is a potential source for reducing policy effectiveness. This study introduces a new method for measuring different types of policy uncertainty in news content using large language models (LLMs). We fine-tune the LLMs to identify different types of uncertainty expressed in newspaper articles based on their context, even if they do not contain specific keywords indicating uncertainty that existing studies have measured. By applying this method to Japan’s monetary policy from 2015 to 2016, we demonstrate that our approach successfully captures the dynamics of monetary policy uncertainty, which vary significantly depending on the type of uncertainty examined.

Keywords: Bank of Japan, Central Bank Communication, Generative Pre-trained Transformer, Large Language Model, Monetary Policy, Policy Uncertainty, text data

Suggested Citation

Ito, Arata and Sato, Masahiro and Ota, Rui, Content-Based Metric on Monetary Policy Uncertainty by Using Large Language Models. Available at SSRN: https://ssrn.com/abstract=5051287 or http://dx.doi.org/10.2139/ssrn.5051287

Arata Ito

Research Institute of Economy, Trade and Industry (RIETI) ( email )

1-3-1 Kasumigaseki
Chiyoda-ku
Tokyo 100-8901
Japan

Masahiro Sato

Tohoku University - Graduate School of International Cultural Studies ( email )

41 Kawauchi
Aoba-ku
Sendai, 980-8576
Japan

Rui Ota (Contact Author)

Meiji University - School of Commerce ( email )

United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
20
Abstract Views
80
PlumX Metrics