Logo
Munich Personal RePEc Archive

Efficient Computation of Portfolio Credit Risk with Chain Default

Ikeda, Yuki (2021): Efficient Computation of Portfolio Credit Risk with Chain Default.

[thumbnail of MPRA_paper_106652.pdf]
Preview
PDF
MPRA_paper_106652.pdf

Download (553kB) | Preview

Abstract

Many banks consider the chain default or bankruptcy when they compute the credit loss distribution. One way to consider the chain default is the good-old Monte Carlo simulation, however, it is typically time-consuming. In this paper, we extend the efficient Monte Carlo simulation using the importance sampling introduced by Glasserman and Li (2005) to realize an efficient Monte Carlo simulation of the Value at Risk (VaR) that allows the chain defaults. In addition, we see that another method, the saddle point approximation, can also be modified for the case of the chain defaults. Moreover, we give a simple method of shifting the means of the multivariate factors using the well-known EM-algorithm to further reduce the variance of the simulated VaR. Simulation studies show that these proposed methods have superior numerical performance.

Atom RSS 1.0 RSS 2.0

Contact us: mpra@ub.uni-muenchen.de

This repository has been built using EPrints software.

MPRA is a RePEc service hosted by Logo of the University Library LMU Munich.