Modeling Portfolio Credit Risk

SRICHANDER RAMASWAMY, PhD

Senior Economist, Bank for International Settlements, Basel, Switzerland

Abstract: Modeling credit risk is more challenging than modeling market risk. Some of these challenges relate to the differences in the conceptual approaches used for modeling credit risk and the data limitations associated with the estimation of key model parameters. Hence, there is invariably a subjective element to the modeling of credit risk. A better understanding of these subjective elements can help practitioners to exercise sound judgment and to raise the right questions when trying to interpret the statistical outputs provided by credit risk models.

This entry describes the building blocks to modeling credit risk. Key elements of the building blocks include probability of default of the issuer; recovery rate in the event of issuer default; and the probabilities of migrating to different credit rating states. Various techniques that can be employed to estimate the probability of issuer default, including their relative merits and limitations, are then discussed. Subsequently, the common approaches to quantifying credit risk are introduced. These include the default mode paradigm, which considers default and no default as two states of the world; and the migration mode paradigm, which includes migrations to other credit rating categories including the default state. The entry concludes with a numerical example to illustrate the various concepts ...

Get Encyclopedia of Financial Models, 3 Volume Set now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.