Capturing Deep Tail Risk via Sequential Learning of Quantile Dynamics

Journal of Economic Dynamics and Control, 2019, 109: 103771

33 Pages Posted: 13 Jun 2019 Last revised: 13 Jan 2020

See all articles by Qi Wu

Qi Wu

City University of Hong Kong (CityUHK)

Xing Yan

City University of Hong Kong

Date Written: May 30, 2019

Abstract

This paper develops a conditional quantile model that can learn long term and short term memories of sequential data. It builds on sequential neural networks and yet outputs interpretable dynamics. We apply the model to asset return time series across eleven asset classes using historical data from the 1960s to 2018. Our results reveal that it extracts not only the serial dependence structure in conditional volatility but also the memories buried deep in the tails of historical prices. We further evaluate its Value-at-Risk forecasts against a wide range of prevailing models. Our model outperforms the GARCH family as well as models using filtered historical simulation, conditional extreme value theory, and dynamic quantile regression. These studies indicate that conditional quantiles of asset return have persistent sources of risk that are not coming from those responsible for volatility clustering. These findings could have important implications for risk management in general and tail risk forecasts in particular.

Keywords: Dynamic Quantile Modeling, Parametric Quantile Functions, Time-varying Higher-order Conditional Moments, Asymmetric Heavy-tail Distribution, Long Short-term Memory, Machine Learning, Neural Network, VaR Forecasts, Financial Risk Management

JEL Classification: G32, C53, C45, C22

Suggested Citation

Wu, Qi and Yan, Xing, Capturing Deep Tail Risk via Sequential Learning of Quantile Dynamics (May 30, 2019). Journal of Economic Dynamics and Control, 2019, 109: 103771, Available at SSRN: https://ssrn.com/abstract=3396084 or http://dx.doi.org/10.2139/ssrn.3396084

Qi Wu (Contact Author)

City University of Hong Kong (CityUHK) ( email )

83 Tat Chee Avenue
Kowloon
Hong Kong

Xing Yan

City University of Hong Kong ( email )

Hong Kong

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
111
Abstract Views
618
rank
268,605
PlumX Metrics