Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder

We present in this paper a method to compute, using generative neural networks, an estimator of the “Value at Risk” for a financial asset. The method uses a Variational Auto Encoder with an 'energy' (a.k.a. Radon-Sobolev) kernel. The result behaves according to intuition and is in line wit...

Descripción completa

Detalles Bibliográficos
Autores principales: Brugière, Pierre, Turinici, Gabriel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Economics/Business
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10165165/
https://www.ncbi.nlm.nih.gov/pubmed/37168774
http://dx.doi.org/10.1016/j.mex.2023.102192
_version_ 1785038213142806528
author Brugière, Pierre
Turinici, Gabriel
author_facet Brugière, Pierre
Turinici, Gabriel
author_sort Brugière, Pierre
collection PubMed
description We present in this paper a method to compute, using generative neural networks, an estimator of the “Value at Risk” for a financial asset. The method uses a Variational Auto Encoder with an 'energy' (a.k.a. Radon-Sobolev) kernel. The result behaves according to intuition and is in line with more classical methods. • Estimation of the Value at Risk with generative neural networks; • No a priori assumptions on the distribution of the returns; • Good practical behavior.
format Online
Article
Text
id pubmed-10165165
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-101651652023-05-09 Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder Brugière, Pierre Turinici, Gabriel MethodsX Economics/Business We present in this paper a method to compute, using generative neural networks, an estimator of the “Value at Risk” for a financial asset. The method uses a Variational Auto Encoder with an 'energy' (a.k.a. Radon-Sobolev) kernel. The result behaves according to intuition and is in line with more classical methods. • Estimation of the Value at Risk with generative neural networks; • No a priori assumptions on the distribution of the returns; • Good practical behavior. Elsevier 2023-04-21 /pmc/articles/PMC10165165/ /pubmed/37168774 http://dx.doi.org/10.1016/j.mex.2023.102192 Text en © 2023 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Economics/Business
Brugière, Pierre
Turinici, Gabriel
Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder
title Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder
title_full Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder
title_fullStr Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder
title_full_unstemmed Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder
title_short Deep learning of value at risk through generative neural network models: The case of the Variational auto encoder
title_sort deep learning of value at risk through generative neural network models: the case of the variational auto encoder
topic Economics/Business
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10165165/
https://www.ncbi.nlm.nih.gov/pubmed/37168774
http://dx.doi.org/10.1016/j.mex.2023.102192
work_keys_str_mv AT brugierepierre deeplearningofvalueatriskthroughgenerativeneuralnetworkmodelsthecaseofthevariationalautoencoder
AT turinicigabriel deeplearningofvalueatriskthroughgenerativeneuralnetworkmodelsthecaseofthevariationalautoencoder

Ejemplares similares