The concepts of model risk and validation

Christian Meyer and Peter Quell

Chapter 3 presented a number of ways in which a QRM might fail. However, these models are meant to be useful tools for risk control and management. Therefore, methods have to be found that can detect and correct, or at least manage, model failure and model imperfection. In this regard, two terms have become prominent: “model risk”, which describes the possibility of QRM failure and its potential consequences, and “validation” as a main weapon against model risk. This chapter will show how to define, and what to expect and not to expect from, these two concepts.

It is not easy to define what model risk and validation are. However, there is a longer tradition of models and of model validation in the natural sciences and engineering, which is a good starting point. Models in social science are usually of a very different kind, while models in finance (and QRMs in particular) lie somewhere between these two extremes.


The rapid increase in computer power since the 1980s has been accompanied by an increasing use of computerised models in the natural sciences and engineering. Model developers and users

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to View our subscription options

You need to sign in to use this feature. If you don’t have a account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here