Does the Quantile Regression Forest Learn More Information on Chinese Systemic Risk?

30 Pages Posted: 15 Jan 2020

See all articles by Yuejiao Duan

Yuejiao Duan

Nankai University - School of Finance

Xiaoyun Fan

Nankai University - School of Finance

Haoran Li

Nankai University - School of Finance

Date Written: December 26, 2019

Abstract

This article applies the quantile regression forest (QRF), which is an improved method for predicting future macroeconomic shocks. We summarize 31 different indexes of Chinese systemic risk and construct predictors using principal component analysis to predict Chinese macroeconomic downside risk. The two forecasting methods, the multiple quantile regression forest (MQRF) and the principal component quantile regression forest (PCQRF), both outperform the quantile regression (QR), the multiple quantile regression (MQR) and the principal component quantile regression (PCQR). Furthermore, we find that with increased systemic risk indexes, more information about the left tail of macroeconomic shocks could be identified by the QRF.

Keywords: Quantile Regression Forest, Systemic Risk, Macroeconomic Forecast

JEL Classification: G10, E37, C53, C55

Suggested Citation

Duan, Yuejiao and Fan, Xiaoyun and Li, Haoran, Does the Quantile Regression Forest Learn More Information on Chinese Systemic Risk? (December 26, 2019). Available at SSRN: https://ssrn.com/abstract=3509691 or http://dx.doi.org/10.2139/ssrn.3509691

Yuejiao Duan

Nankai University - School of Finance ( email )

38 Tongyan Road, Jinnan District
Tianjin, Tianjin 300350
China

Xiaoyun Fan

Nankai University - School of Finance ( email )

38 Tongyan Road, Jinnan District
Tianjin, Tianjin 300350
China

Haoran Li (Contact Author)

Nankai University - School of Finance ( email )

38 Tongyan Road, Jinnan District
Tianjin, Tianjin 300350
China

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
18
Abstract Views
109
PlumX Metrics