Main Menu

【Academic Seminar】Machine Learning for Quantitative Tail Risk Management - Dr. Xing Yan

  • 2019.11.20
  • Event
Machine Learning for Quantitative Tail Risk Management

Topic: Machine Learning for Quantitative Tail Risk Management

Speaker: Dr. Xing Yan, City University of Hong Kong

Time and Date: 14:00 - 15:00, Wednesday, November 20, 2019

Venue: Boardroom, Dao Yuan Building



Extreme events happen more frequently than we think. Forecasting the probability of extreme events in financial markets and the following decision making, are extremely important for investments and regulations. In our research, we design novel machine learning models that capture not only the tail risk of an individual asset but also tail dependence among multiple assets. For individual asset return, we design a parametric quantile function for heavy tail modeling and combine it with an LSTM neural network to describe the dynamic conditional distribution and forecast conditional quantiles. For multiple asset returns, we propose a transformed random vector to separately model their tail dependencies from the correlations, which is a significant advantage over traditional methods for tail dependence modeling. We do adequate numerical experiments to verify our models’ ability for capturing and forecasting tail risks. Besides, we have interesting findings on tail behaviors of assets and they should have important implications for asset pricing.



Dr. Yan is now a postdoc at the School of Data Science, City University of Hong Kong. His research area is financial machine learning and data analytics, where he develops novel machine learning models and data-driven techniques for research problems in financial engineering and finance. He publishes papers in both machine learning and financial engineering communities. Dr. Yan obtained his PhD degree from Department of SEEM, CUHK in 2019. He also holds a master’s degree in computer science from the Chinese Academy of Sciences and a bachelor’s degree in mathematics from Nankai University.