Uncertainty Quantification and Human-Centric Risk Control via Neural–PDE Integration in Complex Volatile Systems

Subject Areas : Financial Mathematics

hosein esmaili ¹ , Mohammad Ali Afshar Kazemi ² , reza radfar ³ , nazanin pilevari ⁴

1 -
2 -
3 -
4 -

Received: 2025-03-22 Accepted : 2025-06-13 Published : 2025-04-23

Keywords: Volatility, Uncertainty, Momentum, Reinforcement,

Abstract :

This article introduces an integrated approach for addressing uncertainty and improving human-oriented risk control by combining differential equation modeling with neural and fuzzy logic enhancements. Differential equation modeling provides a structured mathematical foundation for capturing price dynamics over time, while neural and fuzzy logic components adaptively adjust the model to account for nonlinear behaviors and uncertain market signals. The proposed framework is applied within volatility-aware trading strategies, comparing fixed-exposure and downside-scaled momentum approaches. Using daily data from five major digital currencies spanning 2016 to 2024, the model demonstrates improved prediction accuracy and controlled exposure under volatile conditions. While the adaptive strategy offers reduced drawdowns and more stable weight distributions, it does not universally outperform in return-to-risk metrics. However, the integrated system consistently shows better alignment with market risk regimes, particularly in directional accuracy, confidence calibration, and drawdown control enhancing its practical viability for real-world deployment.

References:

[1] Abbasi, B., Nouri, K., An uncertain renewal stock model for barrier options pricing with floating interest rate, Advances in Mathematical Finance and Applications, 2024;8(4):1154. Doi:10.71716/amfa.2024.24011939
[2] Bányai, A., Tatay, T., Thalmeiner, G., Pataki, L., Optimizing portfolio risk by involving crypto assets in a volatile macroeconomic environment, Risks, 2024;12(4):68. Doi:10.3390/risks12040068
[3] Buse, R., Görgen, K., Schienle, M., Predicting value at risk for cryptocurrencies with generalized ran-dom forests, arXiv preprint arXiv:2203.08224, 2025 [cited 2025 Apr 9]. Doi:10.48550/arxiv.2203.08224
[4] Chen, S., The implementation of modern portfolio theory on new financial assets: evidence from cryptocurrencies, Adv Econ Manag Polit Sci, 2023;56:209-13. Doi:10.54254/2754-1169/56/20231149
[5] Cheng, J., Modelling and forecasting risk dependence and portfolio VaR for cryptocurrencies, Empir Econ, 2023;65(2):899-924. Doi:10.1007/s00181-023-02360-7
[6] Cheong, C.W., Cryptocurrencies vs global foreign exchange risk, J Risk Finance, 2019;20(4):330-51. Doi:10.1108/JRF-11-2018-0178
[7] Darabi, R., Baghban, M., Application of Clayton copula in portfolio optimization and its comparison with Markowitz mean-variance analysis, Advances in Mathematical Finance and Applications, 2018;3(1):33-51. Doi:10.22034/amfa.2018.539133
[8] Deng, Q., Liquidity premium, liquidity-adjusted return and volatility, and extreme liquidity, SSRN Electronic Journal [preprint], 2024 [cited 2025 Apr 9]. Doi:10.2139/ssrn.4694674
[9] Doaei, M., Davarpanah, SH., Sabzi, MZ., ANN-DEA approach of corporate diversification and effi-ciency in Bursa Malaysia, Advances in Mathematical Finance and Applications, 2017;2(1):9-20. Doi:10.22034/amfa.2017.529058
[10] Du, L., Lee, J., Kim, N., Choi, PMS., Schneider, M.J., Got crypto? Evidence from Markowitz, Kataoka, and conditional value-at-risk models. In: Bracker K, Wang K, editors. Fintech, pandemic, and the financial system, Bingley (UK): Emerald Publishing Limited; 2023;113-43. Doi:10.1108/S1569-376720220000022007
[11] Ghanbari, H., Mohammadi, E., Fooeik, A.M.L., Kumar, R.R., Stauvermann, P.J., Shabani, M., Crypto-currency portfolio allocation under credibilistic CVaR criterion and practical constraints, Risks, 2024;12(10):163. Doi:10.3390/risks12100163
[12] Hakim, A., Syuhada, K., Formulating MCoVaR to quantify joint transmissions of systemic risk across crypto and non-crypto markets: a multivariate copula approach, Risks, 2023;11(2):35. Doi:10.3390/risks11020035
[13] Hu, Y., Lindquist, W.B., Fabozzi, F.J., Modeling price dynamics, optimal portfolios, and option valu-ation for crypto assets, J Altern Invest, 2021;24(1):75-93. Doi:10.3905/JAI.2021.1.133
[14] Khojasteh Aliabadi, H.A., Daei-Karimzadeh, S., Iranpour Mobarakeh, M., Zamani Boroujeni, F., De-veloping a model for managing the risk assessment of import declarations in customs based on data anal-ysis techniques, Advances in Mathematical Finance and Applications, 2022;5(4):1075. Doi:10.22034/amfa.2021.1942827.1644
[15] Kirişci, M., An integrated decision-making process for risk analysis of decentralized finance, Neural Comput Appl, 2025. Doi:10.1007/s00521-024-10839-2
[16] Koutsouri, A., Poli, F., Alfieri, E., Petch, M., Distaso, W., Knottenbelt, W.J., Balancing crypto assets and gold: a weighted-risk-contribution index for the alternative asset space. In: Proceedings of MARBLE 2019 Conference; 2019 Jun 30–Jul 3; Santorini, Greece. Cham (CH): Springer International Publishing; 2020;217-32.
[17] Kristjanpoller, W., Minutolo, M.C., A hybrid volatility forecasting framework integrating GARCH, artificial neural network, technical analysis and principal components analysis, Expert Syst Appl, 2018;109:1-11. Doi: 10.1016/j.eswa.2018.05.011
[18] Pankwaen, K., Thongkairat, S., Saijai, W., Global cross-market trading optimization using iterative combined algorithm: a multi-asset approach with stocks and cryptocurrencies, Preprints.org [preprint]. 2025 [cited 2025 Apr 9]. Doi:10.20944/preprints202503.1146.v1
[19] Papenbrock, J., Schwendner, P., Sandner, P.G., Can adaptive seriational risk parity tame crypto port-folios? SSRN Electronic Journal [preprint], 2021. doi:10.2139/ssrn.3877143
[20] Saidane, M., Risk assessment in cryptocurrency portfolios: a composite hidden Markov factor anal-ysis framework, Stat Optim Inf Comput, 2024;12(2):463-87. Doi:10.19139/soic-2310-5070-1837
[21] Xiang, Q., Cryptocurrency assets valuation prediction based on LSTM, neural network, and deep learning hybrid model, Appl Comput Eng. 2024; 49:265-72. Doi:10.54254/2755-2721/49/20241346
[22] Zaj, M.M., Samavi, M.E., Koosha, E., Measurement of Bitcoin daily and monthly price prediction error using grey model, back propagation artificial neural network and integrated model of grey neural network, Advances in Mathematical Finance and Applications, 2022:535-53. Doi:10.22034/amfa.2020.1881110.1315
[23] Zhang, X., The impact of Bitcoin and gold in the portfolio: a research based on copula, Adv Econ Manag Polit Sci, 2024;107:160-5. Doi:10.54254/2754-1169/2024.ga18165