GAN-MC: a Variance Reduction Tool for Derivatives Pricing

TL;DR

GAN-MC introduces a parameter-free, generative model-based Monte Carlo approach for derivatives pricing that outperforms traditional arbitrage-based and machine learning models, especially with limited data or unknown asset dynamics.

Contribution

The paper presents a novel variance reduction method using generative models for derivatives valuation, improving accuracy and generalizability over existing models.

Findings

GAN-MC outperforms Black-Scholes and other machine learning models in real market data.

The model demonstrates superior variance reduction in Monte Carlo simulations.

It is effective even with limited training samples and unknown underlying dynamics.

Abstract

We propose a parameter-free model for estimating the price or valuation of financial derivatives like options, forwards and futures using non-supervised learning networks and Monte Carlo. Although some arbitrage-based pricing formula performs greatly on derivatives pricing like Black-Scholes on option pricing, generative model-based Monte Carlo estimation(GAN-MC) will be more accurate and holds more generalizability when lack of training samples on derivatives, underlying asset's price dynamics are unknown or the no-arbitrage conditions can not be solved analytically. We analyze the variance reduction feature of our model and to validate the potential value of the pricing model, we collect real world market derivatives data and show that our model outperforms other arbitrage-based pricing models and non-parametric machine learning models. For comparison, we estimate the price of derivatives using Black-Scholes model, ordinary least squares, radial basis function networks, multilayer perception regression, projection pursuit regression and Monte Carlo only models.