SMU SOE Seminar Series (August 26, 2024): ChatGPT, Stock Market Predictability and Links to the Macroeconomy

Please click here if you are unable to view this page.

TOPIC:

CHATGPT, STOCK MARKET PREDICTABILITY AND LINKS TO THE MACROECONOMY

ABSTRACT

We find that positive news extracted by ChatGPT from the front pages of the Wall Street Journal is related to macroeconomic conditions and can predict monthly stock market returns. Consistent with existing theories, investors tend to underreact to positive news, especially during periods of economic downturns, high information uncertainty, and high news novelty. However, negative news is negatively associated with contemporaneous returns and has no predictive power. We find further that traditional methods, such as word lists and BERT, fail to have comparable predictability, and ChatGPT appears at present the best in capturing economic news about the market risk premium.

Keywords: LLMs, ChatGPT, Textual Analysis, NLP, Return Predictability

JEL Codes: C22, C53, G11, G12, G17

Click here to view the CV.
Click here to view the paper.

PRESENTER

Wu Zhu
Tsinghua University

RESEARCH FIELDS

Finance
AI (Artificial Intelligence)
Big Data
Network Economics
Portfolio Management Macroeconomics
Innovation
Chinese Economy

DATE:

26 August 2024 (Monday)

TIME:

4pm - 5.30pm

VENUE:

Meeting Room 5.1, Level 5
School of Economics
Singapore Management University
90 Stamford Road
Singapore 178903

© Copyright 2024 by Singapore Management University. All Rights Reserved.
Internal recipients of SMU, please visit https://smu.sg/emailrules, on how to filter away this EDM.
For all other recipients, please click here to unsubscribe.