A Financial Engineering Approach to Cryptocurrency Portfolio Risk Management Using Copula-GARCH Models, Extreme Value Theory, and Machine Learning
Keywords:
Cryptocurrency, Portfolio Risk Management, Copula-GARCH, Extreme Value Theory, Machine Learning, Value at Risk, Conditional Value at Risk, Financial EngineeringAbstract
This study aimed to develop and evaluate an integrated financial engineering framework for cryptocurrency portfolio risk management among Iranian investors by combining Copula-GARCH models, Extreme Value Theory, and machine-learning techniques. This applied quantitative study used a longitudinal financial time-series design based on daily data from ten major cryptocurrencies, including Bitcoin, Ethereum, Binance Coin, Ripple, Cardano, Dogecoin, Litecoin, Stellar, Tron, and Bitcoin Cash, from January 1, 2019, to December 31, 2024. After converting synchronized daily closing prices into logarithmic returns, the final dataset included 21,910 asset-return observations. Data were analyzed using descriptive diagnostics, Jarque-Bera normality tests, ARCH-LM tests, GARCH-family volatility models, copula dependence structures, Extreme Value Theory, Value at Risk, Conditional Value at Risk, portfolio optimization, machine-learning forecasting models, and VaR backtesting procedures. The inferential results showed significant non-normality and conditional heteroskedasticity in all cryptocurrency return series, as indicated by Jarque-Bera and ARCH-LM tests (p < 0.001). GARCH-family estimations confirmed strong volatility persistence across all assets, with GJR-GARCH and EGARCH models outperforming standard specifications for most cryptocurrencies. Copula-GARCH and EVT results showed that the equal-weighted portfolio had the highest tail-risk exposure, whereas the machine-learning-enhanced CVaR portfolio produced the most favorable risk profile. In VaR backtesting, the variance-covariance and historical simulation models failed the Kupiec and Christoffersen coverage tests, while the Copula-GARCH-EVT-ML model produced the most accurate 99% VaR performance, with observed violations matching expected violations and non-significant coverage test results. Among machine-learning models, Extreme Gradient Boosting achieved the lowest prediction error and strongest directional accuracy. The findings indicate that cryptocurrency portfolio risk cannot be adequately managed through static correlation-based or variance-based models. Integrating Copula-GARCH, Extreme Value Theory, and machine learning provides a more robust framework for estimating volatility, nonlinear dependence, extreme downside risk, and optimized portfolio allocation in cryptocurrency markets.
References
[1] F. Fang et al., "Cryptocurrency Trading: A Comprehensive Survey," Financial Innovation, vol. 8, no. 1, 2022, doi: 10.1186/s40854-021-00321-6.
[2] M. Zhang, B. Zhu, Z. Li, S. Jin, and Y. Xia, "Relationships Among Return and Liquidity of Cryptocurrencies," Financial Innovation, vol. 10, no. 1, 2024, doi: 10.1186/s40854-023-00532-z.
[3] M. I. Contreras-Valdez, J. A. N. Mora, and G. B. Perales, "Bitcoin in Portfolio Selection: A Multivariate Distribution Approach," Sage Open, vol. 12, no. 2, 2022, doi: 10.1177/21582440221096124.
[4] D. Li, Y. Shi, L. Xu, Y. Xu, and Y. Zhao, "Dynamic Asymmetric Dependence and Portfolio Management in Cryptocurrency Markets," Finance Research Letters, vol. 48, p. 102829, 2022, doi: 10.1016/j.frl.2022.102829.
[5] H. M. Tenkam, J. Clément, and S. M. Mwambi, "Optimization and Diversification of Cryptocurrency Portfolios: A Composite Copula-Based Approach," Applied Sciences, vol. 12, no. 13, p. 6408, 2022, doi: 10.3390/app12136408.
[6] J. Clément and M. Mbong, "A Particle Swarm Optimization Copula-Based Approach With Application to Cryptocurrency Portfolio Optimisation," Journal of Risk and Financial Management, vol. 15, no. 7, p. 285, 2022, doi: 10.3390/jrfm15070285.
[7] V. Jeleskovic, C. Latini, Z. I. Younas, and M. A. S. Al‐Faryan, "Cryptocurrency Portfolio Optimization: Utilizing a GARCH‐copula Model Within the Markowitz Framework," Journal of Corporate Accounting & Finance, vol. 35, no. 4, pp. 139-155, 2024, doi: 10.1002/jcaf.22721.
[8] E. M. Kimani, A. Ngunyi, and J. Mung’atu, "Modelling Dependence of Cryptocurrencies Using Copula Garch," Journal of Mathematical Finance, vol. 13, no. 03, pp. 321-338, 2023, doi: 10.4236/jmf.2023.133020.
[9] A. BenSaïda, "The Linkage Between Bitcoin and Foreign Exchanges in Developed and Emerging Markets," Financial Innovation, vol. 9, no. 1, 2023, doi: 10.1186/s40854-023-00454-w.
[10] M. Mili and A. Bouteska, "Forecasting Nonlinear Dependency Between Cryptocurrencies and Foreign Exchange Markets Using Dynamic Copula: Evidence From GAS Models," The Journal of Risk Finance, vol. 24, no. 4, pp. 464-482, 2023, doi: 10.1108/jrf-04-2022-0074.
[11] H. Mzoughi, Y. Ghabri, and K. Guesmi, "Crude Oil, Crypto-Assets and Dependence: The Impact of the COVID-19 Pandemic," International Journal of Energy Sector Management, vol. 17, no. 3, pp. 552-568, 2022, doi: 10.1108/ijesm-10-2021-0016.
[12] A. Lamine, A. Jeribi, and T. Fakhfakh, "Spillovers Between Cryptocurrencies, Gold and Stock Markets: Implication for Hedging Strategies and Portfolio Diversification Under the COVID-19 Pandemic," Journal of Economics Finance and Administrative Science, vol. 29, no. 57, pp. 21-41, 2023, doi: 10.1108/jefas-09-2021-0173.
[13] U. Sharma and M. Karmakar, "Are Gold, USD, and Bitcoin Hedge or Safe Haven Against Stock? The Implication for Risk Management," Review of Financial Economics, vol. 41, no. 1, pp. 43-64, 2022, doi: 10.1002/rfe.1160.
[14] D. Maitra, M. U. Rehman, S. R. Dash, and S. H. Kang, "Do Cryptocurrencies Provide Better Hedging? Evidence From Major Equity Markets During COVID-19 Pandemic," The North American Journal of Economics and Finance, vol. 62, p. 101776, 2022, doi: 10.1016/j.najef.2022.101776.
[15] A. Díaz, C. Esparcia, and R. López, "The Diversifying Role of Socially Responsible Investments During the COVID-19 Crisis: A Risk Management and Portfolio Performance Analysis," Economic Analysis and Policy, vol. 75, pp. 39-60, 2022, doi: 10.1016/j.eap.2022.05.001.
[16] D. Krężołek and K. Piontek, "Volatility and Models Based on the Extreme Value Theory for Gold Returns," Statistics in Transition New Series, vol. 25, no. 2, pp. 1-22, 2024, doi: 10.59170/stattrans-2024-012.
[17] F. Jin, J. Li, and G. Li, "Modeling the Linkages Between Bitcoin, Gold, Dollar, Crude Oil, and Stock Markets: A GARCH‐EVT‐Copula Approach," Discrete Dynamics in Nature and Society, vol. 2022, no. 1, 2022, doi: 10.1155/2022/8901180.
[18] J. H. Eita and C. R. T. Djemo, "Quantifying Foreign Exchange Risk in the Selected Listed Sectors of the Johannesburg Stock Exchange: An SV-EVT Pairwise Copula Approach," International Journal of Financial Studies, vol. 10, no. 2, p. 24, 2022, doi: 10.3390/ijfs10020024.
[19] L. Cao, R. Sun, T. Ma, and C. Liu, "On Asymmetric Correlations and Their Applications in Financial Markets," Journal of Risk and Financial Management, vol. 16, no. 3, p. 187, 2023, doi: 10.3390/jrfm16030187.
[20] U. Sharma and M. Karmakar, "Asymptotic Dependence and Its Impact on Hedging Effectiveness: An Examination of Stock, Currency, and Commodity Futures," Journal of Futures Markets, vol. 44, no. 11, pp. 1750-1786, 2024, doi: 10.1002/fut.22546.
[21] E. Jones, T. Matsui, and W. Knottenbelt, "Stablecoins as Dry Powder: A Copula-Based Risk Analysis of Cryptocurrency Markets," 2026, doi: 10.48550/arxiv.2603.23480.
[22] R. J. Oben, M. Seraj, and Ş. Z. Eyüpoğlu, "Volatility and Return Spillovers Among US Traditional Technology Stocks, Decentralized Finance Instruments And conventional Cryptocurrencies: Implications for Portfolio Optimization," Review of Behavioral Finance, vol. 17, no. 5, pp. 807-834, 2025, doi: 10.1108/rbf-12-2024-0377.
[23] B. A. Nugroho, "The Stability of Islamic Cryptocurrencies and Copula-Based Dependence With Alternative Crypto and Fiat Currencies," Isra International Journal of Islamic Finance, vol. 15, no. 2, pp. 80-97, 2023, doi: 10.55188/ijif.v15i2.543.
[24] D. Song, Machine Learning for Price Prediction and Risk -Adjusted Portfolio Optimization in Cryptocurrencies (In Machine Learning and Modeling Techniques in Financial Data Science). 2025, pp. 321-356.
[25] X. Deng, F. Geng, and Y. Lu, "A Novel ARMA- GARCH-Sent-EVT-Copula Portfolio Model With Investor Sentiment," 2022, doi: 10.21203/rs.3.rs-2064723/v1.
[26] F. M. Müller, T. W. Gössling, S. S. Santos, and M. B. Righi, "A Comparison of Range Value at Risk (RVaR) Forecasting Models," Journal of Forecasting, vol. 43, no. 3, pp. 509-543, 2023, doi: 10.1002/for.3043.
[27] N. Shahbazi and S. Barkhordari, "Optimizing a portfolio comprising selected stocks and cryptocurrencies," Budget and Finance Strategic Research, vol. 6, no. 2, pp. 11-35, 2025.
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2025 Hooshmand Mahdavi; Hiedar Foroughnejad , Mohammad Sadri (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
