Interest rate risk of Chinese commercial banks based on the GARCH-EVT model

This paper examines the Value-at-Risk (VaR) and statistical properties of the daily price return of Shanghai banks' overnight offered rate (SHIBOR) after China's interest rate marketization. A two-stage approach combining GARCH-type models with extreme value theory (EVT) is used. A Markov regime switching model analyzes regime states, and the performance of different VaR models is compared. Results show the extreme value approach provides better estimates at the 99% confidence level, with the EGARCH-GED model being the most suitable GARCH-type model. Back-testing supports the approach's appropriateness for improving daily risk management in commercial banks. Policy implications are discussed to guide commercial banks' activities.

Xin Chen, Zhangming Shan, Decai Tang, Biao Zhou, Valentina Boamah