Universal approximation of credit portfolio losses using Restricted Boltzmann Machines

Giuseppe Genovese, Ashkan Nikeghbali, Nicola Serra and Gabriele Visentin

Papers from arXiv.org

Abstract: We introduce a new portfolio credit risk model based on Restricted Boltzmann Machines (RBMs), which are stochastic neural networks capable of universal approximation of loss distributions. We test the model on an empirical dataset of default probabilities of 1'012 US companies and we show that it outperforms commonly used parametric factor copula models -- such as the Gaussian or the t factor copula models -- across several credit risk management tasks. In particular, the model leads to better fits for the empirical loss distribution and more accurate risk measure estimations. We introduce an importance sampling procedure which allows risk measures to be estimated at high confidence levels in a computationally efficient way and which is a substantial improvement over the Monte Carlo techniques currently available for copula models. Furthermore, the statistical factors extracted by the model admit an interpretation in terms of the underlying portfolio sector structure and provide practitioners with quantitative tools for the management of concentration risk. Finally, we show how to use the model for stress testing by estimating stressed risk measures (e.g. stressed VaR) under various macroeconomic stress test scenarios, such as those specified by the FRB's Dodd-Frank Act stress test.

Date: 2022-02, Revised 2023-04
New Economics Papers: this item is included in nep-cmp and nep-rmg
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2202.11060 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2202.11060

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().