Multi-Asset Spot and Option Market Simulation

TL;DR

This paper develops a realistic multi-asset market simulator for spot and options using normalizing flows and an arbitrage-free autoencoder, enabling scalable calibration and high-fidelity simulation of complex market dynamics.

Contribution

It introduces a novel combination of normalizing flows and an arbitrage-free autoencoder to simulate multi-asset markets with preserved dynamics and no static arbitrage.

Findings

Simulators accurately replicate market data.

Calibration method effectively captures joint asset distributions.

High fidelity in simulated market dynamics.

Abstract

We construct realistic spot and equity option market simulators for a single underlying on the basis of normalizing flows. We address the high-dimensionality of market observed call prices through an arbitrage-free autoencoder that approximates efficient low-dimensional representations of the prices while maintaining no static arbitrage in the reconstructed surface. Given a multi-asset universe, we leverage the conditional invertibility property of normalizing flows and introduce a scalable method to calibrate the joint distribution of a set of independent simulators while preserving the dynamics of each simulator. Empirical results highlight the goodness of the calibrated simulators and their fidelity.