CorrGAN: Sampling Realistic Financial Correlation Matrices Using Generative Adversarial Networks

TL;DR

CorrGAN introduces a generative adversarial network-based method to produce realistic financial correlation matrices, aiding in trading, risk management, and scientific validation of empirical finance.

Contribution

This is the first application of GANs to generate realistic financial correlation matrices, advancing both methodology and practical financial analysis.

Findings

GANs recover key stylized facts of empirical correlation matrices

Generated matrices are realistic and useful for financial applications

First documented use of GANs for this purpose in literature

Abstract

We propose a novel approach for sampling realistic financial correlation matrices. This approach is based on generative adversarial networks. Experiments demonstrate that generative adversarial networks are able to recover most of the known stylized facts about empirical correlation matrices estimated on asset returns. This is the first time such results are documented in the literature. Practical financial applications range from trading strategies enhancement to risk and portfolio stress testing. Such generative models can also help ground empirical finance deeper into science by allowing for falsifiability of statements and more objective comparison of empirical methods.