The purpose of this chapter

The purpose of this chapter is to show how to combine the information from the spliced joint distribution of changes in market risk factors (made up of the ‘body’ and of the excited components) with the chosen utility function to obtain a coherent allocation to the various sub-portfolios in the presence of (i.e., taking into due account) stress events. The adjective ‘coherent’ stresses that the allocation has been arrived at by taking into account in a consistent manner the investor's preferences over the outcomes associated with both normal and exceptional market conditions. In our methodology, ‘protection trades’ (such as, say, purchasing out-of-the-money puts or buying CDS protection) are not attached as an ex post afterthought to an optimization previously carried out assuming a stable investing universe. Rather, they are an integral and, again, coherent part of the process.

The emphasis of this chapter is computational. In this respect, it is arguably less ‘exciting’ than the conceptual and methodological parts of the book. However, there is little point in developing interesting ideas unless they can be implemented effectively. From this perspective this apparently mundane chapter is therefore one of the most important of the book.

We also present in this chapter a method to explore the sensitivity of the outputs to one important component of the Bayesian-net construction, i.e., the probability mass associated with the ‘nothing happens’ event.