The 23th Academic Luncheon of the Digital Technology and Finance

Abstract：

In natural and social sciences, modeling rare events (known as "black swan" events) has extensive and important applications. Extreme value theory is an important tool for studying rare events. However, traditional extreme value theories are based on the assumption that data is independently and identically distributed, which does not align with the characteristics of actual time series data and has certain limitations. Recently, some literatures have begun to propose time-varying extreme value time series models that can capture the dynamic characteristics of rare events. First, this article reviews the modeling methods of traditional extreme value theory. Then, it introduces the latest progress in dynamic extreme value time series. Finally, it provides an outlook on the future development of dynamic extreme value theory and its potential applications in financial fields such as asset pricing, investment portfolios, and risk management.

Speaker Introduction：

Zhang Chuanhai, PhD, Associate Professor, School of Finance, Zhongnan University of Economics and Law. His research interests include financial markets, financial measurement and financial risk, as well as Fintech and big data. His research papers have been published in: Economic Research, Systems Engineering Theory and Practice, Journal of Management Engineering, Mathematical Statistics and Management, Journal of Econometrics, Quantitative Finance, Pacific-Basin Finance Journal, Finance Research Letters, International Review of Financial Analysis and Economic Modelling and other domestic and foreign journals.