Generating Realistic Stock Market Order Streams

Junyi Li, Xintong Wang, Yaoyang Lin, Arunesh Sinha, Michael P. Wellman

Abstract:

We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks.
We model the order stream as a stochastic process with finite history dependence, and employ a conditional Wasserstein GAN to capture history dependence of orders in a stock market.
We test our approach with actual market and synthetic data on a number of different statistics, and find the generated data to be close to real data.

Keywords: application in finance, stock markets, generative models

TL;DR: We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks.