Integrating Statistical Models and Machine Learning for Derivatives Portfolio Valuation and Risk Assessment

Regulatory scrutiny of banks’ internal models has intensified, demanding improvements in quantitative risk methodologies and the implementation of new regulatory measures. Repeated portfolio revaluation makes these calculations computationally challenging, notably under the Fundamental Review of the Trading Book (FRTB). In this context, we examine the computational implementation of market risk models, focusing on the practical calculation of Value at Risk (VaR) and Expected Shortfall (ES). Given the complexity of trading portfolios, these models rely on proxies and simplifying assumptions for computational efficiency. This paper explores the use of Gaussian processes (GPs), a powerful machine learning technique, to accelerate the revaluation of derivative portfolios. Trained on datasets generated by sophisticated pricing models, the GP algorithm learns valuation functions and subsequently performs rapid and accurate revaluations. Numerical tests on an equity derivatives portfolio demonstrate that Gaussian process regression (GPR) significantly reduces computation time while maintaining a high accuracy for market risk assessment.