Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lütkebohmert, Eva, Sester, Julian
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.16525
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912121599557632
author Lütkebohmert, Eva
Sester, Julian
author_facet Lütkebohmert, Eva
Sester, Julian
contents We propose a new deep learning approach for the quantification of name concentration risk in loan portfolios. Our approach is tailored for small portfolios and allows for both an actuarial as well as a mark-to-market definition of loss. The training of our neural network relies on Monte Carlo simulations with importance sampling which we explicitly formulate for the CreditRisk${+}$ and the ratings-based CreditMetrics model. Numerical results based on simulated as well as real data demonstrate the accuracy of our new approach and its superior performance compared to existing analytical methods for assessing name concentration risk in small and concentrated portfolios.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16525
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Measuring Name Concentrations through Deep Learning
Lütkebohmert, Eva
Sester, Julian
Risk Management
General Finance
We propose a new deep learning approach for the quantification of name concentration risk in loan portfolios. Our approach is tailored for small portfolios and allows for both an actuarial as well as a mark-to-market definition of loss. The training of our neural network relies on Monte Carlo simulations with importance sampling which we explicitly formulate for the CreditRisk${+}$ and the ratings-based CreditMetrics model. Numerical results based on simulated as well as real data demonstrate the accuracy of our new approach and its superior performance compared to existing analytical methods for assessing name concentration risk in small and concentrated portfolios.
title Measuring Name Concentrations through Deep Learning
topic Risk Management
General Finance
url https://arxiv.org/abs/2403.16525