Financial Engineering Workshop - Sergio Caprioli (Intesa SanPaolo)

Presenter: Sergio Caprioli (Intesa SanPaolo)

Presentation title
Quantifying Credit Portfolio sensitivity to asset correlations with interpretable generative neural networks

Abstract
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.

Bio
Sergio Caprioli holds an MSc in Statistics and Corporate Strategies and a BSc in Statistics and Information Technologies from the University La Sapienza (Rome). With over a decade of experience in Risk Management and Credit Controls, in the last years he has been acting as Expert Coordinator within Intesa SanPaolo ICAAP and Operational Risks Internal Validation department in Milan. In this role, he has led projects related to ICAAP, IFRS9, Model Risk, Credit and Country Risk validation. Sergio has also lectured as adjunct university professor and guest lecturer and he has been a featured speaker at various banking and finance workshops.

Faculty Events | Website | View More Events

Contact the organizers