Skip to Content
You are currently on the new version of our website. Access the old version .
EntropyEntropy
  • Article
  • Open Access

5 June 2015

14 Pages

Tail Risk Constraints and Maximum Entropy

,
and
1
Department of Applied Mathematics & Statistics, Johns Hopkins University, Baltimore, MD 21218-2608, USA
2
Department of Economics, Mathematics and Statistics, Birkbeck, University of London, London WC1E 7HX, UK
3
Polytechnic School of Engineering, New York University, New York, NY 11201, USA
*
Author to whom correspondence should be addressed.
This article belongs to the Special Issue Information Processing in Complex Systems

Abstract

Portfolio selection in the financial literature has essentially been analyzed under two central assumptions: full knowledge of the joint probability distribution of the returns of the securities that will comprise the target portfolio; and investors’ preferences are expressed through a utility function. In the real world, operators build portfolios under risk constraints which are expressed both by their clients and regulators and which bear on the maximal loss that may be generated over a given time period at a given confidence level (the so-called Value at Risk of the position). Interestingly, in the finance literature, a serious discussion of how much or little is known from a probabilistic standpoint about the multi-dimensional density of the assets’ returns seems to be of limited relevance. Our approach in contrast is to highlight these issues and then adopt throughout a framework of entropy maximization to represent the real world ignorance of the “true” probability distributions, both univariate and multivariate, of traded securities’ returns. In this setting, we identify the optimal portfolio under a number of downside risk constraints. Two interesting results are exhibited: (i) the left- tail constraints are sufficiently powerful to override all other considerations in the conventional theory; (ii) the “barbell portfolio” (maximal certainty/ low risk in one set of holdings, maximal uncertainty in another), which is quite familiar to traders, naturally emerges in our construction.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.