×

cCorrGAN

swMATH ID: 44878
Software Authors: Marti, Gautier; Goubet, Victor; Nielsen, Frank
Description: cCorrGAN: conditional correlation GAN for learning empirical conditional distributions in the elliptope. 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.
Homepage: https://arxiv.org/abs/2107.10606
Keywords: generative adversarial networks; correlation matrices; elliptope geometry; empirical distributions; quantitative finance; Monte Carlo simulations
Related Software: geomstats; CorrGAN; QuantGAN; POT
Cited in: 2 Documents

Citations by Year