Quantifying Credit Portfolio sensitivity to asset correlations with interpretable generative neural networks
This work addresses risk management for financial institutions by providing interpretable tools for credit portfolio sensitivity analysis, though it is incremental as it builds on prior GAN-based methods.
The researchers tackled the problem of quantifying credit portfolio Value-at-Risk sensitivity to asset correlations by using Variational Autoencoders to generate synthetic financial correlation matrices, achieving a more interpretable latent space representation that captures factors impacting portfolio diversification.
In this research, we propose a novel approach for the quantification of credit portfolio Value-at-Risk (VaR) sensitivity to asset correlations with the use of synthetic financial correlation matrices generated with deep learning models. In previous work Generative Adversarial Networks (GANs) were employed to demonstrate the generation of plausible correlation matrices, that capture the essential characteristics observed in empirical correlation matrices estimated on asset returns. Instead of GANs, we employ Variational Autoencoders (VAE) to achieve a more interpretable latent space representation. Through our analysis, we reveal that the VAE latent space can be a useful tool to capture the crucial factors impacting portfolio diversification, particularly in relation to credit portfolio sensitivity to asset correlations changes.