Risk-Neutral Market Simulation

TL;DR

This paper introduces a risk-neutral market simulator for a single underlying asset that preserves no arbitrage, uses neural spline flows for realistic sampling, and closely matches historical data.

Contribution

It presents a novel low-dimensional, arbitrage-free risk-neutral simulation method employing neural spline flows for high realism and data fidelity.

Findings

Effective drift removal demonstrated

High fidelity to historical data achieved

Simulator closely matches real market distributions

Abstract

We develop a risk-neutral spot and equity option market simulator for a single underlying, under which the joint market process is a martingale. We leverage an efficient low-dimensional representation of the market which preserves no static arbitrage, and employ neural spline flows to simulate samples which are free from conditional drifts and are highly realistic in the sense that among all possible risk-neutral simulators, the obtained risk-neutral simulator is the closest to the historical data with respect to the Kullback-Leibler divergence. Numerical experiments demonstrate the effectiveness and highlight both drift removal and fidelity of the calibrated simulator.