The 358th Wenlan Financial Forum

Abstract：

In the era of Big Data, with the deep application of artificial intelligence technologies, investors are more capable than ever of effectively tracking the massive amount of information in capital markets. Whether investors' attention to multi-dimensional information can enhance aligned expectations is of great significance for a profound understanding of expectation formation in capital markets. Based on multi-dimensional characteristics of Chinese listed companies, this paper introduces a machine learning framework to construct an expectation alignment index and explores how investor expectations under multi-feature learning affect asset pricing. The empirical results show that lower levels of expectation alignment lead to lower future stock returns, indicating that improving investor expectation alignment contributes to the stability and sustainable development of China's capital market. Furthermore, from the perspectives of short-sale constraints and limited arbitrage, this paper demonstrates that mispricing is the mechanism through which investor expectation alignment positively correlates with future stock returns. Additionally, the study finds that accounting information quality significantly negatively correlates with the pricing effect of expectation alignment, while the number of features exhibits a non-linear impact on the pricing effect, initially strengthening and then weakening. Heterogeneity analysis of investors with different trading styles reveals that differences in preferences for financial signals lead to variations in the pricing effect of expectation alignment. Finally, the paper provides development recommendations regarding investor information processing, information quality construction in capital markets, and the application of AI technology in expectation management.

Speaker Introduction：

Guohao Tang, Ph.D. in Economics (Finance), is an Associate Professor and Doctoral Supervisor at the School of Finance and Statistics, Hunan University. He holds several notable honors and appointments, including being selected for the "Huxiang Young Talents" program, serving as a Visiting Scholar at Washington University in St. Louis, and acting as Deputy Director of the Department of Financial Technology and Engineering. He is also a Council Member of the Quantitative Finance Association, China Society of Optimization, Overall Planning and Economic Mathematics, and a Researcher at the Hunan Provincial Key Laboratory for Macroeconomic Big Data Mining and Applications.Dr. Tang has presided over multiple research projects, including those funded by the National Natural Science Foundation of China, the Ministry of Education Humanities and Social Sciences Fund, the Hunan Provincial Natural Science Foundation (General and Youth Programs), and provincial-level teaching reform projects.He currently serves as the Co-Editor-in-Chief of Annals of Economics and Finance, the first English-language economics and finance journal in China to be included in the SSCI. His primary research focuses on financial technology, financial machine learning, and empirical asset pricing with Chinese characteristics. His work has been published in renowned domestic and international journals such as the Journal of Financial and Quantitative Analysis, Journal of Banking & Finance, Journal of Economic Dynamics & Control, Journal of International Money and Finance, as well as leading Chinese journals including Journal of Management Science , Journal of Financial Research , China Economic Quarterly , and Economic Perspectives .His policy research and advisory submissions have received instructions from the Vice Premier of the State Council, the Provincial Party Secretary, and the Governor of Hunan Province. Dr. Tang has been recognized with several awards, including the Hunan Provincial Outstanding Master's Thesis Supervisor (2024), the First Prize in the 7th National University Economics and Management Experimental Teaching Case Competition (2024), and multiple provincial and university-level teaching honors.