Acceleration of multi-factor Merton model Monte Carlo simulation via Importance Sampling and GPU parallelization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F16%3A86098980" target="_blank" >RIV/61989100:27240/16:86098980 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27740/16:86098980

Výsledek na webu

<a href="http://dx.doi.org/10.1201/b21348-19" target="_blank" >http://dx.doi.org/10.1201/b21348-19</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1201/b21348-19" target="_blank" >10.1201/b21348-19</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Acceleration of multi-factor Merton model Monte Carlo simulation via Importance Sampling and GPU parallelization

Popis výsledku v původním jazyce

Credit risk refers to the risk of losses due to unexpected credit events, as a default of a counterparty. The modelling and controlling of credit risk is a very important topic within banks. Very popular and frequently used tools for modelling credit risk are multi-factor Merton models. Practical implementation of these models requires time-consuming Monte Carlo (MC) simulations, which significantly limits their usability in daily credit risk calculation. In this paper we present acceleration techniques of Merton model Monte Carlo simulations, concretely parallel GPU implementation and Importance Sampling (IS) employment. As the importance sampling distribution we choose the Gaussian mixture model and for calculating the IS shifted probability distribution we use the Cross-Entropy (CE) method. The speed-up results are demonstrated using portfolio Value at Risk (VaR) and Expected Shortfall (ES) calculation.

Název v anglickém jazyce

Acceleration of multi-factor Merton model Monte Carlo simulation via Importance Sampling and GPU parallelization

Popis výsledku anglicky

Credit risk refers to the risk of losses due to unexpected credit events, as a default of a counterparty. The modelling and controlling of credit risk is a very important topic within banks. Very popular and frequently used tools for modelling credit risk are multi-factor Merton models. Practical implementation of these models requires time-consuming Monte Carlo (MC) simulations, which significantly limits their usability in daily credit risk calculation. In this paper we present acceleration techniques of Merton model Monte Carlo simulations, concretely parallel GPU implementation and Importance Sampling (IS) employment. As the importance sampling distribution we choose the Gaussian mixture model and for calculating the IS shifted probability distribution we use the Cross-Entropy (CE) method. The speed-up results are demonstrated using portfolio Value at Risk (VaR) and Expected Shortfall (ES) calculation.

Druh

D - Stať ve sborníku

CEP obor

BB - Aplikovaná statistika, operační výzkum

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Applied Mathematics in Engineering and Reliability : proceedings of the 1st International Conference on Applied Mathematics in Engineering and Reliability : Ho Chi Minh City, Vietnam, 4-6 May 2016

ISBN

978-1-138-02928-6

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

107-118

Název nakladatele

CRC PRESS-TAYLOR &amp; FRANCIS GROUP

Místo vydání

London

Místo konání akce

Ho Či Minovo Město

Datum konání akce

4. 5. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000387432400015