Classification of RBA monetary policy announcements using ChatGPT

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

ChatGPT is a tool that has gained much attention and has accelerated the adoption of Artificial Intelligence across many applications. Using monetary policy decisions made by the Reserve Bank of Australia (RBA), we test whether ChatGPT's classifications of monetary policy announcements are consistent with market-observed characteristics, whether this has changed with the update from GPT-3.5 to GPT-4, and whether this provides additional informativeness for changes in the yield implied by interest rate futures. Our results indicate that, regardless of statement readability, ChatGPT provides a classification of hawkish / dovish tone that is consistent with “Target Surprises” and “Path Surprises” and although it seems to improve in the latest version has more difficulty with “sentiment” classification. However, this information does not appear to help to explain changes in interest rate markets on the day of the policy announcement.
Original languageEnglish
Article number104514
Number of pages10
JournalFinance Research Letters
Volume58
Issue numberC
DOIs
Publication statusPublished - Dec 2023

Fingerprint

Dive into the research topics of 'Classification of RBA monetary policy announcements using ChatGPT'. Together they form a unique fingerprint.

Cite this