cCorrGAN: Conditional Correlation GAN for Learning Empirical Conditional Distributions in the Elliptope

@article{Marti2021cCorrGANCC,
  title={cCorrGAN: Conditional Correlation GAN for Learning Empirical Conditional Distributions in the Elliptope},
  author={Gautier Marti and Victor Goubet and Frank Nielsen},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.10606}
}
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. 

Figures from this paper

References

SHOWING 1-10 OF 31 REFERENCES
Quant GANs: deep generation of financial time series
TLDR
Quant GANs is introduced, a data-driven model which is inspired by the recent success of generative adversarial networks (GANs), and results highlight that distributional properties for small and large lags are in an excellent agreement and dependence properties such as volatility clusters, leverage effects, and serial autocorrelations can be generated by the generator function of Quant GAns, demonstrably in high fidelity. Expand
Time Series Simulation by Conditional Generative Adversarial Net
TLDR
This paper proposes to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data and presents a real data analysis including a backtesting to demonstrate CGAN is able to outperform the Historic Simulation, a popular method in market risk analysis for the calculation of VaR. Expand
Generative adversarial networks for financial trading strategies fine-tuning and combination
TLDR
This work proposes the use of Conditional Generative Adversarial Networks (cGANs) for trading strategy calibration and aggregation, and suggests that cGANs are a suitable alternative for strategy calibrated and combination, providing outperformance when the traditional techniques fail to generate any alpha. Expand
Modeling financial time-series with generative adversarial networks
TLDR
A deep neural networks based approach, generative adversarial networks (GANs) for financial time- series modeling is presented, which produces a time-series that recovers the statistical properties of financialTime Series such as the linear unpredictability, the heavy-tailed price return distribution, volatility clustering, leverage effects, the coarse-fine volatility correlation, and the gain/loss asymmetry. Expand
Matrix Evolutions: Synthetic Correlations and Explainable Machine Learning for Constructing Robust Investment Portfolios
TLDR
This study organizes an explainable machine learning program to establish a link from the simulated matrices to relative investment performance, and demonstrates the potential of Matrix Evolutions in a machine learning case study for robust portfolio construction in a multi-asset universe. Expand
Building Diversified Portfolios that Outperform Out of Sample
In this article, the author introduces the Hierarchical Risk Parity (HRP) approach to address three major concerns of quadratic optimizers, in general, and Markowitz’s critical line algorithm (CLA),Expand
Building Diversified Portfolios that Outperform Out-of-Sample
In this article, the author introduces the Hierarchical Risk Parity (HRP) approach to address three major concerns of quadratic optimizers, in general, and Markowitz’s critical line algorithm (CLA),Expand
Generative adversarial network based telecom fraud detection at the receiving bank
TLDR
A new generative adversarial network (GAN) based model is proposed to calculate for each large transfer a probability that it is fraudulent, such that the bank can take appropriate measures to prevent potential fraudsters to take the money if the probability exceeds a threshold. Expand
Riemannian batch normalization for SPD neural networks
TLDR
A Riemannian batch normalization (batch- norm) algorithm is introduced, which generalizes the one used in Euclidean nets and derives a new manifold-constrained gradient descent algorithm working in the space of SPD matrices, allowing to learn the batchnorm layer. Expand
Simulating realistic correlation matrices for financial applications: correlation matrices with the Perron–Frobenius property
ABSTRACT This article is concerned with the simulation of correlation matrices with realistic properties for financial applications. Previous studies found that the major part of observed correlationExpand
...
1
2
3
4
...