CorrGAN: Sampling Realistic Financial Correlation Matrices Using Generative Adversarial Networks

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.

References in corpus (10)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Hierarchical Structure in Financial Markets
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Cleaning large correlation matrices: tools from random matrix theory
• NetGAN: Generating Graphs via Random Walks
• A Geometric Approach to Covariance Matrix Estimation and its Applications to Radar Problems
• High Fidelity Speech Synthesis with Adversarial Networks
• Geometry Score: A Method For Comparing Generative Adversarial Networks
• Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination
• Shrinkage and spectral filtering of correlation matrices: a comparison via the Kullback-Leibler distance

Cited by in corpus (3)

• Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
• cCorrGAN: Conditional Correlation GAN for Learning Empirical Conditional Distributions in the Elliptope
• Implementing a Hierarchical Deep Learning Approach for Simulating Multi-Level Auction Data