This repository implements methods from the following papers and resources, spanning classical quantitative finance, stochastic volatility modeling, and modern machine learning approaches to derivatives pricing and hedging.
- Deep Hedging: Hedging Derivatives Under Multiple Constraints (Buehler et al., 2019) Applies supervised learning to minimize hedging error with transaction costs and market frictions
- The Volatility Surface: A Practitioner's Guide (Gatheral, 2006)
- A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options (Heston, 1993) Original stochastic volatility model with semi-analytic pricing formulas
- Stochastic Volatility Modelling (Bergomi, 2016) Comprehensive treatment of stochastic volatility modeling and hedging implications
- A Novel Pricing Method for European Options Based on Fourier-Cosine Series Expansions (Fang & Oosterlee, 2008) Introduces the COS method for fast and accurate option pricing using Fourier-cosine expansions
- Precise option pricing by the COS method--How to choose the truncation range (Junike & Pankrashkin, 2022) Another way to choose a truncation interval in the COS method
- Option Pricing when Underlying Stock Returns are Discontinuous (Merton, 1976) Foundational paper on jump-diffusion models for option pricing
- The Variance Gamma Process and Option Pricing (Madan et al., 1998) Introduction of the Variance Gamma model for capturing heavy tails and skewness
- Monte Carlo Methods in Financial Engineering (Glasserman, 2003) Comprehensive reference for Monte Carlo methods in finance
- COS Method (Fang & Oosterlee, 2008) - Implemented in
pricing.heston.cos - Heston Model (Heston, 1993) - Implemented in
models.heston - Deep Hedging (Buehler et al., 2019) - Implemented in
ml.models.hedge_net - Jump-Diffusion Models (Merton, 1976) - Planned for future implementation
- Diffusion Models for Path Generation - Planned for integration with
generative-models-journey