Having a valid and up-to-date credit risk model (or models) is one of the most important aspects in today’s risk management. The models require quite a bit of technical as well as practical know-how. Introduction to Credit Risk Modeling serves this purpose well. It provides a somewhat technical view on credit risk modeling with plenty of examples. Overall, I would say that the book is more applied than theoretical. Quite a number of proofs are skipped (and referenced) or written very loosely, with more space used for examples and explanations. Given the overall structure of the book it would best fit the practitioner’s needs. For students it can also be of great use, as an introductory course for credit risk models. A great first step into credit risk modeling.
The books starts off with a chapter introducing a reader to the general aspects of credit risk, differentiating between expected and unexpected losses and emphasizing the importance of economic capital, where most things come together from the institution’s point of view. Chapter 2 by itself is valuable; it deals with correlated defaults, and is a little gem not found in many other books. It is presented very nicely, providing a much needed overview of the methods considered in this area. Chapters 5 and 6 stand out as well; they discuss capital allocation and term structure of default probability. Capital allocation and risk measures are today one of the most talked-about topics. The book provides a nice coherent overview of the methods used in capital allocation. Credit derivatives and CDOs provide the last two chapters of the book.
The book is written in a mixture of theorem-proof and applied styles. This is rarely seen: usually if the book is applied it lacks the theoretical aspects. I find this rather pleasing, as it gives the reader the edge of theoretical exposition, which is extremely important. The references at the end of the book provide another step for a reader interested in filling both the theoretical and applied side. After all, one needs to build these models in practice. One really useful side of the book is that it provides step-by-step guide to methods presented. This should be really appreciated in industry and among students. Combining this with computational exercises should provide another dimension to the understanding.
Given the somewhat theoretical nature of the book, the reader should have some background in graduate level probability and statistics courses. A good working knowledge of a statistical programming language such as SAS or R would also be good. Computational aspects of the methods are not a focal point of the book but with some data and some initiative from the reader could provide the edge.
Ita Cirovic Donev holds a Masters degree in statistics from Rice University. Her main research areas are in mathematical finance; more precisely, statistical methods for credit and market risk. Apart from the academic work she does statistical consulting work for financial institutions in the area of risk management.