Explainable Predictive Modeling for Value-at-Risk and Expected Shortfall: An Empirical Study of Investment Portfolios

Author

Henry Sarpong


Abstract

 The increasing complexity of global financial markets, heightened asset price volatility, and evolving investment risk exposures have intensified the demand for accurate, transparent, and adaptive portfolio risk assessment frameworks. Traditional financial risk models, particularly Value-at-Risk (VaR) and Expected Shortfall (ES), remain fundamental to measuring potential investment losses but frequently encounter limitations when capturing nonlinear dependencies, extreme market events, and rapidly changing financial conditions. This study examines the application of explainable predictive modelling techniques to enhance the estimation and interpretation of VaR and ES across diversified investment portfolios. Particular emphasis is placed on econometric forecasting, machine learning algorithms, volatility modelling, and explainable artificial intelligence methods for identifying influential risk factors and predicting potential portfolio losses. The study further considers empirical evaluation through historical financial data, backtesting procedures, comparative model performance, and risk attribution analysis. Additionally, challenges involving model uncertainty, data quality, interpretability, and regulatory accountability are critically examined. Ultimately, the study highlights the potential of integrating predictive accuracy with transparent model explanations to strengthen portfolio risk management, support informed investment decisions, and improve financial resilience under uncertain market conditions.



Keywords

Value-at-Risk; Expected Shortfall; Explainable Artificial Intelligence; Predictive Modelling; Portfolio Risk Management; Financial Market Volatility.



Full Text:

Download Paper PDF


References


  1. Zamani M, Emamverdi G, Noorifard Y, Hamidian M, Jafari SM. Predicting Value At Risk: An Artificial Intelligence Approach. Quarterly Journal of Quantitative Economics (JQE). 2024 Aug 22;21(2):1-33.
  2. Dolon MS. Deployment and performance evaluation of hybrid machine learning models for stock price forecasting and risk prediction in volatile markets. American Journal of Scholarly Research and Innovation. 2025 Jul 5;4(01):287-319.
  3. Sigauke C, Moroke N, Makatjane K, Shoko C. A deep learning forecasting of downside risk: Application of a combined ESRNN-VAE. Frontiers in Applied Mathematics and Statistics. 2025 Sep 15;11:1662252.
  4. Knoors B. Quantifying Value at Risk and Expected Shortfall in Pricing Derivatives using the Geometric Brownian Motion. Available at SSRN 5337343. 2025 Jun 20.
  5. Shaar R, Kato H, Hikmat RF. Predicting Value at Risk in Investment Portfolio Using Monte Carlo Simulation: The Case of The Syrian Internasional Islamic Bank. El-Jizya: Jurnal Ekonomi Islam. 2025 Jun 26;13(1):115-34.
  6. Trucíos C, Tiwari AK, Alqahtani F. Value-at-risk and expected shortfall in cryptocurrencies’ portfolio: A vine copula–based approach. Applied Economics. 2020 May 20;52(24):2580-93.
  7. Vahdati M, Karimi MR, Rahimi A. Evaluating the Performance of a Hybrid Model in Improving Key Risk Management Metrics in Financial Markets. Business, Marketing, and Finance Open. 2025:1-26.
  8. Chukwunweike J. Coordinating PLC-based load shedding and variable-speed drives to prevent transformer overloading during industrial production peaks. Int J Electr Data Commun. 2025;6(2 Pt B):118-135. doi:10.22271/27083969.2025.v6.i2b.109.
  9. Naimoli A. The information content of sentiment indices in forecasting value at risk and expected shortfall: a complete realized exponential GARCH-X approach. International Economics. 2023 Dec 1;176:100459.
  10. FROLOV A, Boiko R, Rudevska V, Butenko D, Moisiiakha A. Evaluating modern quantitative methods for investment portfolio management under market uncertainty. Journal of Applied Economic Sciences. 2025 Sep 1;20(16):427.
  11. Bhetwal S, Bastakoti R, Acharya N, Gupta GK, Bhandari AB. Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware. arXiv preprint arXiv:2606.01338. 2026 May 31.
  12. Abraham R, El-Chaarani H, Tao Z. Predictors of excess return in a green energy equity portfolio: Market risk, market return, value-at-risk and or expected shortfall?. Journal of Risk and Financial Management. 2022 Feb 14;15(2):80.
  13. Colombo D. Portfolio Risk Management: Theoretical Models and Quantitative Tools to Optimize Financial Investments. Davide Colombo; 2025 Sep 3.
  14. Arian H, Moghimi M, Tabatabaei E, Zamani S. Encoded value-at-risk: a predictive machine for financial risk management. arXiv preprint arXiv:2011.06742. 2020 Nov 13.
  15. Asante, A., Daramola, G., Davis, R. W., & Kumar, S. (2025). Environmentally Friendly Chelation for Enhanced Algal Biomass Deashing. Phycology, 5(3), 32. https://doi.org/10.3390/phycology5030032
  16. Chen JM. On exactitude in financial regulation: Value-at-risk, expected shortfall, and expectiles. Risks. 2018 Jun 1;6(2):61.
  17. BOȚOROGA CA, HOROBEȚ A, Belascu L. ASSESSING MARKET RISK DURING FINANCIAL CRISES-AN APPLICABLE METHOD OF USING VALUE AT RISK AND EXPECTED SHORTFALL IN INVESTMENTS. Revista Economică. 2021 May 1;73(3):51.
  18. Nasir A, Khan KI, Mata MN, Mata PN, Martins JN. Optimisation of time-varying asset pricing models with penetration of value at risk and expected shortfall. Mathematics. 2021 Feb 17;9(4):394.
  19. Melina M, Sukono, Napitupulu H, Mohamed N. Modeling of machine learning-based extreme value theory in stock investment risk prediction: a systematic literature review. Big data. 2025 Jun 1;13(3):161-80.
  20. Lockwood E. Predicting the unpredictable: Value-at-risk, performativity, and the politics of financial uncertainty. Review of international political economy. 2015 Jul 4;22(4):719-56.
  21. Oluwatobi Alebiosu. Comparative analysis of public-private partnership legislation driving electricity infrastructure expansion, renewable energy investment, and economic resilience nationally. Int J Foreign Trade Int Bus 2025;7(2):239-249. DOI: 33545/26633140.2025.v7.i2c.262
  22. Harmantzis FC, Miao L, Chien Y. Empirical study of value‐at‐risk and expected shortfall models with heavy tails. The journal of risk finance. 2006 Mar 1;7(2):117-35.
  23. Samuel Addo. Harnessing AI-powered financial forecasting tools to improve risk management, investment strategies, and overall corporate profitability across industries. International Journal of Science and Research Archive, 2023, 09(02), 1175-1192. Article DOI: https://doi.org/10.30574/ijsra.2023.9.2.0653
  24. Halbleib SM, Pohlmeier W, Prokhorov A, Rockinger M. Combining value-at-risk and expected shortfall forecasts using machine learning techniques. Advancing systematic and factor investing strategies using alternative data and machine learning. 2021 Sep;96.
  25. Melina, Sukono, Napitupulu H, Mohamed N. A conceptual model of investment-risk prediction in the stock market using extreme value theory with machine learning: a semisystematic literature review. Risks. 2023 Mar 14;11(3):60.
  26. Blom HM, De Lange PE, Risstad M. Estimating value-at-risk in the EURUSD currency cross from implied volatilities using machine learning methods and quantile regression. Journal of Risk and Financial Management. 2023 Jun 27;16(7):312.
  27. Daramola G. Reducing environmental compliance failures through automated regulatory reporting and real-time risk escalation in industrial operations. Int J Res Publ Rev. 2025;6(3):10328-10340. doi:10.55248/gengpi.06.0326.2410.
  28. Alexander C, Dakos M. Assessing the accuracy of exponentially weighted moving average models for Value-at-Risk and Expected Shortfall of crypto portfolios. Quantitative Finance. 2023 Mar 4;23(3):393-427.
  29. Bloss M, Ernst D, Geisinger L. Extreme Value Theory and Gold Price Extremes, 1975–2025: Long-Term Evidence on Value-at-Risk and Expected Shortfall. Commodities. 2025 Oct 16;4(4):24.
  30. Makatjane K, Shoko C. Explainable deep learning for financial risk: Joint VaR and ES forecasting using ESRNN in the Bitcoin market. African Finance Journal. 2025 Jun 1;27(1):53-69.
  31. Moustati I, Gherabi N. A novel hybrid XAI-RL framework for IoB-driven risk-adjusted portfolio optimization. Scientific African. 2025 Dec 31:e03175.
  32. Samuel Addo. Causal AI for strategic business planning: uncovering latent drivers of long-term organizational performance and resilience. World Journal of Advanced Research and Reviews, 2025, 26(2), 895-912. Article DOI: https://doi.org/10.30574/wjarr.2025.26.2.1738
  33. Hossain MA. Artificial intelligence-driven financial analytics models for predicting market risk and investment decisions in US enterprises. ASRC Procedia: Global Perspectives in Science and Scholarship. 2025 Apr 29;1(01):1066-95.
  34. Bhandari, A. B. (2026). Quality Control Frameworks for Electronic Health Record Data Workflows in Resource-Constrained Settings: A Structured Review with Implications for Global Health Information Management. Current Journal of Applied Science and Technology, 45(8), 1–16. https://doi.org/10.9734/cjast/2026/v45i84728
  35. Li C. Research on financial risk prediction and management models based on big data analysis. International Journal of High Speed Electronics and Systems. 2025 Jun 2:2540620.

 

 

 

 

 

Share your valuable work from Social Media Buttons