Robust Optimisation and Portfolio Selection: The Cost of Robustness
32 Pages Posted: 16 Aug 2008
Date Written: July 17, 2008
Robust optimization is a tractable alternative to stochastic programming particularly suited for problems in which parameter values are unknown, variable, and their distributions are uncertain. We evaluate the cost of robustness of the robust counterpart to the maximum return portfolio optimization problem. The uncertainty of asset returns is modelled by polyhedral uncertainty sets as opposed to the earlier proposed ellipsoidal sets. We derive the robust model from a min-regret perspective and examine the properties of robust models with respect to portfolio composition. We investigate the effect of different definitions of the bounds on the uncertainty sets and show that robust models yield well diversified portfolios, in terms of the number of assets and asset weights.
Keywords: robust optimization, portfolio selection
Suggested Citation: Suggested Citation