[Under uncertainty] there is no scientific basis on which to form any calculable probability whatever. We simply don't know. Nevertheless, the necessity for action and for decision compels us as practical men to do our best to overlook this awkward fact and to behave exactly as we should if we had behind us … a series of prospective advantages and disadvantages, each multiplied by its appropriate probability waiting to be summed. J M Keynes, 1937

This book deals with asset allocation in the presence of stress events or user-specified scenarios. To arrive at the optimal allocation, we employ a classic optimization procedure – albeit one which is adapted to our needs. The tools employed to deal consistently and coherently with stress events and scenario analysis are Bayesian nets.

The idea of applying the Bayesian-net technology, recently introduced in Rebonato (2010a, b), Rebonato and Denev (2012) and Denev (2013) in the context of stress testing and asset allocation, seems a very straightforward one. So straightforward, indeed, that one may well wonder whether a 500+ page book is truly needed, especially given that two thirty-page articles are already available on the topic.

We decided that this book was indeed needed when we began using this technique in earnest in practical asset-allocation situations. We soon discovered that many slips are possible between the cup of a promising idea and the lips of real-life applications, and that only a thorough understanding of these intermediate steps can turn a promising idea into something really useful and practical.