cCorrGAN: Conditional Correlation GAN for Learning Empirical Conditional Distributions in the Elliptope
This addresses a domain-specific problem in quantitative finance for portfolio risk analysis, but appears incremental as it adapts existing GAN methods to a specialized mathematical structure.
The paper tackles the problem of approximating conditional distributions in the elliptope of correlation matrices using conditional GANs, applying it to simulate correlated returns in quantitative finance for comparing portfolio risk methods.
We propose a methodology to approximate conditional distributions in the elliptope of correlation matrices based on conditional generative adversarial networks. We illustrate the methodology with an application from quantitative finance: Monte Carlo simulations of correlated returns to compare risk-based portfolio construction methods. Finally, we discuss about current limitations and advocate for further exploration of the elliptope geometry to improve results.