Incorporating Value-at-Risk in Portfolio Selection: An Evolutionary Approach
Chueh‐Yung Tsao, Chao-Kung Liu · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2006
The mean-variance framework for portfolio selection should be revised when investor's concern is the downside risk.This is especially true when the asset returns are not normal.In this paper, we incorporate value-at-risk (VaR) in portfolio selection and the mean-VaR framework is proposed.Due to the twoobjective optimization problem faced by the mean-VaR framework, an evolutionary multi-objective approach is applied to construct the mean-VaR efficient frontier.In particular, the NSGA-II is considered here.From the empirical analysis it is found that the risk-averse investor might inefficiently allocate his wealth if his decision is based on the mean-variance framework.