Experiments in Robust Portfolio Optimization

Daniel Bienstock (danocolumbia.edu)

Abstract: We present experimental results on portfolio optimization problems with return errors under the robust optimization framework. We use several a histogram-like model for return deviations, and a model that allows correlation among errors, together with a cutting-plane algorithm which proves effective for large, real-life data sets.

Keywords: robust optimization, integer programming, value-at-risk, portfolio optimization

Category 1: Robust Optimization

Category 2: Integer Programming ((Mixed) Integer Nonlinear Programming )

Category 3: Applications -- OR and Management Sciences (Finance and Economics )

Citation: Columbia Center for Financial Engineering Report 2007-01 Columbia University, January 2007

Download: [PDF]

Entry Submitted: 02/16/2007
Entry Accepted: 02/20/2007
Entry Last Modified: 02/27/2007

Modify/Update this entry