Quantifying Crypto Portfolio Risk: A Simulation-Based Framework Integrating Volatility, Hedging, Contagion, and Monte Carlo Modeling

Abstract

Four key modules—volatility stress testing, stablecoin hedging, contagion modeling, and Monte Carlo simulation—are integrated into our modular, simulation-based framework for cryptocurrency portfolio risk. Stress design through volatility and correlation shocks, portfolio construction under static weights for controlled comparison, and multivariate price dynamics under tractable assumptions (log-normal baseline with correlation coupling) are all formalized by the mathematical architecture. Value-at-Risk (VaR) and Expected Shortfall (ES) backtesting, sensitivity analysis (shock magnitudes and rolling windows), and calibration diagnostics are all part of the empirical validation using daily BTC, ETH, and USDT data (2020–2024). A roadmap for future extensions, such as GARCH-type volatility models, jump-diffusion processes, copula-based contagion, network adjacency based on on-chain data, and EVT-based tail validation, is provided. We also acknowledge the limitations of distributional assumptions and linear dependence. The result is a reproducible, crypto-native risk framework with clear pathways for enhanced realism and broader asset coverage.