Risk-Neutral Market Simulation

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, but also highly realistic in the sense that among all possible risk-neutral simulators, they are a minimal Kullback-Leibler divergence to the historical data. We demonstrate the effectiveness with numerical experiments which highlight both the drift removal and the fidelity of the calibrated simulator