Deep Weighted Monte Carlo: A hybrid option pricing framework using neural networks

TL;DR

This paper introduces a hybrid option pricing framework combining Variational Autoencoders, neural networks, and Weighted Monte Carlo methods to efficiently price vanilla and exotic options using low-dimensional implied volatility representations.

Contribution

It presents a novel neural network-based weight assignment method integrated with VAE to model asset dynamics and improve option pricing accuracy.

Findings

Successfully trains neural network to assign path weights from latent space

Framework effectively prices vanilla and exotic options

Reduces noise in volatility surface for better pricing signals

Abstract

Recent studies have demonstrated the efficiency of Variational Autoencoders (VAE) to compress high-dimensional implied volatility surfaces into a low dimensional representation. Although this method can be effectively used for pricing vanilla options, it does not provide any explicit information about the dynamics of the underlying asset. In our work we present an effective way to overcome this problem. We use a Weighted Monte Carlo approach to first generate paths from a simple a priori Brownian dynamics, and then calculate path weights to price options correctly. We develop and successfully train a neural network that is able to assign these weights directly from the latent space. Combining the encoder network of the VAE and this new "weight assigner" module, we are able to build a dynamic pricing framework which cleanses the volatility surface from irrelevant noise fluctuations, and then can price not just vanillas, but also exotic options on this idealized vol surface. This pricing method can provide relative value signals for option traders.