Novel modeling for assessment of extreme values risk in cryptocurrencies portfolio
摘要
This study addresses risk management for a ten-dimensional cryptocurrency portfolio, focusing on value at risk, expected shortfall, and range value at risk. It introduces a hybrid model combining the ARMA-EGARCH approach with flexible bulk and tails extreme value distribution and copula functions to improve risk measurement. The results show that the ARMA-EGARCH-EVT copula model better captures dependencies and outperforms traditional risk assessment methods (such as historical simulations and the variance covariance paradigm). This study underscores the potential of using a novel extreme value theory probability model to enhance risk assessment and provide valuable insights for investors and financial policymakers.