PORTFOLIO OPTIMIZATION WITH DRAWDOWN （投资组合优化和减少）.pdf

Implemented in Portfolio Safeguard by AOrD PORTFOLIO OPTIMIZATION WITH DRAWDOWN CONSTRAINTS 1 2 2 Alexei Chekhlov , Stanislav Uryasev , Michael Zabarankin Risk Management and Financial Engineering Lab Center for Applied Optimization Department of Industrial and Systems Engineering University of Florida, Gainesville, FL 32611 Date: January 13, 2003 Correspondence should be addressed to: Stanislav Uryasev Abstract We propose a new one -parameter family of risk functions defined on portfolio return sample -paths, which is called conditional drawdown-at-risk (CDaR). These risk functions depend on the portfolio drawdown (underwater) curve considered in active portfolio management. For some value of the tolerance parameter a , the CDaR is defined as the mean of the worst (1 a ) 100% drawdowns. The CDaR risk function contains the maximal drawdown and average drawdown as its limiting cases. For a particular example, we find optimal portfolios with constraints on the maximal drawdown, average drawdown and several intermediate cases between these two. The CDaR family of risk functions originates from the conditional value-at-risk (CVaR) measure. Some recommendations on how to select the optimal risk measure for getting practically stable portfolios are provided. We solved a real life portfolio allocation problem using the proposed risk functions. 1. Introduction Optimal portfolio allocation is a longstanding issue in both practical portfolio management and academic research on