Estimating market risk in volatile environments remains a major challenge, as traditional GARCH-type models often struggle to capture nonlinear dynamics. This paper proposes a hybrid Value-at-Risk (VaR) framework that integrates GARCH volatility forecasts with a Double Deep Q-Network (DDQN) reinforcement learning classifier. By reframing VaR estimation as a classification problem, the model adaptively adjusts risk thresholds based on predicted low- and high-risk return regimes. Using more than 16 years of Euro Stoxx 50 data, the framework achieves 79.4% test accuracy and substantially reduces both the frequency and the temporal clustering of VaR violations. Backtesting confirms compliance with the Kupiec and Christoffersen tests, while Extreme Value Theory supports its ability to model tail risk. The resulting approach offers a statistically robust, capital-efficient, and regulatory-aligned solution for proactive financial risk management.
Pokou, Fredy, Sadefo Kamdem, Jules, Benhmad, François. Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models. // Computational Economics. – 2026. – DOI: 10.1007/s10614-025-11191-w. – URL: http://link.springer.com/openurl/fulltext?id=doi:10.1007/s10614-025-11191-w
Pokou, Fredy, Sadefo Kamdem, Jules, Benhmad, & François (2026). Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models. Computational Economics. https://doi.org/10.1007/s10614-025-11191-w
Pokou, et al. “Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models.” Computational Economics, 2026. doi:10.1007/s10614-025-11191-w.
@article{Pokou2026,
title = {Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models},
author = {Pokou and Fredy and Kamdem, Sadefo and Jules and Benhmad and François},
journal = {Computational Economics},
year = {2026},
doi = {10.1007/s10614-025-11191-w},
url = {http://link.springer.com/openurl/fulltext?id=doi:10.1007/s10614-025-11191-w}
}
Extensive explorations have been undertaken regarding carbon price forecasting, particularly in light of the significance of the emission trading system (ETS), one of the most economical strategies for addressing global warming....
The environmental disruption caused by engineering project construction conflicts with the green transformation goals of the construction industry. Encouraging contractors to adopt environmentally friendly behaviors is essential for...
To mitigate environmental issues and climate change, the large-scale development of CCUS has become a global consensus. Although market players are key driving forces to promote the application of CCUS technology, the significant...
This study investigates the impacts of localized uncertainties on the state-level housing markets in the US from 1990 to 2023. Using the quantile vector autoregression (QVAR), it discovers that adverse uncertainty shocks can enhance...
While machine learning models are acclaimed for their superior predictive performance in the era of big data, their practical application in credit scoring has been limited by a lack of interpretability comparable to that of logistic...