A0309
Title: Evaluating tail risk in Bitcoin using stochastic volatility and jump models under Basel standards
Authors: Huei-Wen Teng - National Yang Ming Chiao Tung University (Taiwan) [presenting]
Hsin-Pei Huang - National Yang Ming Chiao Tung University (Taiwan)
Yu Chuan Shih - National Yang Ming Chiao Tung University (Taiwan)
Abstract: The measurement of tail risk is investigated in cryptocurrency markets through the lens of value-at-risk (VaR) and expected shortfall (ES), with a focus on regulatory relevance under the Basel III framework. Using daily Bitcoin data from 2018 to 2024, the performance of four models widely used in financial risk modeling is assessed: Black-Scholes (BS), stochastic volatility (SV), stochastic volatility with jumps (SVJ), and stochastic volatility with correlated jumps (SVCJ). Each model is used to generate one-step-ahead forecasts of VaR and ES over rolling windows and evaluated across multiple holding periods (1, 14, and 28 days) and confidence levels (95\% and 99\%). Backtesting results based on the traffic light approach, Kupiec's proportion of failures (POF) test, Christoffersen's conditional coverage (CC) test, and the Acerbi-Szekely (Z1Z3) tests for ES reveal that the SVCJ model consistently achieves superior accuracy in capturing extreme losses, particularly for longer horizons. The findings indicate that jointly modeling volatility clustering and jump dependence, as in the SVCJ framework, substantially enhances the accuracy and conservativeness of tail risk estimation for digital assets. This underscores the critical role of model selection in crypto risk management and offers practical implications for financial institutions and regulators aiming to integrate cryptocurrencies into capital adequacy and stress testing frameworks.
