How to choose my stochastic volatility parameters? A review

2025-12-22

AI Summary

This paper addresses the parameter calibration challenge in stochastic volatility (SV) and stochastic local volatility (SLV) models for financial derivative pricing. It systematically reviews and comparatively analyzes three dominant estimation paradigms—historical calibration, option-market-based calibration, and Bayesian inference—clarifying their respective applicability domains and practical limitations. Methodologically, the study integrates statistical inference, maximum likelihood estimation, least-squares calibration, Monte Carlo simulation, and implied volatility surface modeling to construct an operational framework for model parameter selection. Its key contribution lies in the first systematic cross-method integration and boundary delineation of heterogeneous, multi-source calibration approaches. Empirical validation demonstrates that the proposed framework significantly enhances pricing robustness—particularly under short maturities and high-volatility regimes—and improves dynamic hedging accuracy relative to conventional calibration practices.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Based on the existing literature, this article presents the different ways of choosing the parameters of stochastic volatility models in general, in the context of pricing financial derivative contracts. This includes the use of stochastic volatility inside stochastic local volatility models.

Problem

• Reviewing parameter selection methods for stochastic volatility models
• Focusing on financial derivative pricing applications
• Including stochastic local volatility model integration

Innovation

• Reviewing parameter selection methods for stochastic volatility models
• Focusing on financial derivative pricing applications
• Incorporating stochastic volatility within stochastic local volatility frameworks