Date: 21 November 2024 (Thu)
Webinar
Webinar Series:
Capital Marketing Development: China and Asia
Large Language Models and Return Prediction in China
21 November 2024, Thursday
10:00 am – 11:10 am, Thursday (Singapore Time, UTC+8)
[Large Language Models and Return Prediction in China]
The authors examine whether large language models (LLMs) can extract contextualized representation of Chinese public news articles to predict stock returns. Based on representativeness and influences, the authors consider seven LLMs: BERT, RoBERTa, FinBERT, Baichuan, ChatGLM, InternLM, and their ensemble model. The authors show that news tones and return forecasts extracted by LLMs from Chinese news significantly predict future returns. The value-weighted long-minus-short portfolios yield annualized returns between 35% and 67%, depending on the model. Building on the return predictive power, the authors further investigate its implications for information efficiency. The authors show the assimilation speed of the LLM signals is two days, and they contain fundamental information. The signals can be especially helpful under higher frictions, when firms have less efficient information environments, more complex news, and higher retail holdings. Interestingly, heterogeneous investors load their future trades oppositely on LLM signals upon news releases. These findings suggest LLMs can be helpful in processing public news, and thus contribute to overall market efficiency.
Speaker:
Lin TAN, PhD Candidate, PBC School of Finance, Tsinghua University
Co-authors:
Huihang WU, Research Associate, PBC School of Finance, Tsinghua University
Xiaoyan ZHANG, Xinyuan Chair Professor of Finance, Associate Dean, PBC School of Finance, Tsinghua University and Senior Fellow, ABFER
Discussant:
Yinan SU, Assistant Professor of Finance, Carey Business School, Johns Hopkins University
-----------
Event Website
https://abfer.org/events/abfer-events/webinar-series/385:webinarseries-cmd-37
-----------
About the Webinar
Financial market development goes hand-in-hand with economic growth. The development of China's capital markets in terms of size, regulations, capability, and efficiency has been impressive. China may now even lead globally in some dimensions, notably e-payments systems. Yet, China's capital markets are still a work-in-progress facing both generic and unique challenges. Other Asian capital markets have even greater uneven development. Some in advanced Asian economies have acquired globally acclaimed reputation and capabilities while various regulatory and structural weaknesses dwarf others. Corporations and investors have been inclined to arbitrage cross-border regulatory and developmental gaps; so the very uneven status of capital markets across Asia is a policy issue for the governments in the entire region and perhaps globally. Analysing the positive and negative lessons in the functioning of Asia's capital markets, and identifying reforms and applications of technology that could further improve Asian capital markets' allocation efficiency, financial inclusion, and forewarning against reforms that might cause problems can benefit practitioners, policymakers and researchers, and can contribute significantly to overall prosperity.
The ABFER and the University of Chicago's Becker Friedman Institute China (BFI-China), in collaboration with National University of Singapore (NUS) Business School, Shanghai Advanced Institute of Finance (SAIF), The Chinese University of Hong Kong (CUHK) Department of Economics, CUHK-Shenzhen and Tsinghua University PBC School of Finance (Tsinghua PBCSF), hope to provide a virtual network to benefit researchers, policymakers, and practitioners from Asia and beyond.