Selection of the right risk measures for portfolio allocation

Abstract

An optimisation framework is proposed to enable investors to select the right risk measures in portfolio selection. Verification is deployed by performing experiments in developed markets (e.g., the US stock market), emerging markets (e.g., the South Korean stock market) and global investments. A preselection procedure dealing with large datasets is also introduced to eliminate stocks that have low diversification potential before running the portfolio optimisation model. Portfolios are evaluated by four performance indices, i.e., the Sortino ratio, the Sharpe ratio, the Stutzer performance index, and the Omega measure. Experimental results demonstrate that high performance and also well-diversified portfolios are obtained if modified value-at-risk, variance, or semi-variance is concerned whereas emphasising only skewness, kurtosis or higher moments in general produces low performance and poorly diversified portfolios. In addition, the preselection applied to large datasets results in portfolios that have not only high performance but also high diversification degree.