Two Staged Portfolio Optimizations

Abstract

The primary goal of this work is to determine if an active portfolio optimization strategy utilizing a two staged optimization approach outperforms an ordinary optimization technique.   Both portfolio optimization models are based on Markowitz’s Modern Portfolio Theory (MPT), which relies on assets’ mean, variance, and correlation to maximize returns at any given level of risk.

For the two staged optimization approach the process of optimization is applied twice.  In the first stage, it is used to select an optimal portfolio of industries, and in the second stage optimization is applied to determine an optimal portfolio consisting of stocks within each industry.

Our research indicates that portfolios formed based on ordinary optimization outperforms two staged portfolios and Market indexes by 37% during a bear market (2002) and outperforms Dow Jones Industrial Average and  S&P 500 by more than 13% during a bull market (2003). The performance of each model was determined by the capital gains and the dividend returns during the 2002 to 2003 time period.