A New Portfolio Model Based On Semivariance And The Empirical Research On Shanghai Stock Market And CvaR Risk Meaning Practice Under Transaction Cost

1. A new Portfolio Model Based on Semivariance and the Empirical Research on Shanghai Stock MarketThe major problem facing investors has always been the maximization of wealth in a world of uncertainty. Portfolio selection is how to allocate wealth among alternative assets of a basket.The mean-variance approach by Markowitz provides a fundamental basis for portfolio construction in a single period. But there are some shortcomings in this model. The most important contribution of this model is that it quantifies the risk by using the variance, which doesn't enable to differentiate buyer and seller in real investment. And this model does not mean investors' feel to deal with the dispersion.As a capital market, the loss and return have lots of differences to confirm risk. The portfolio revenue will produce risk when the practical revenue rate will be less than the expectative revenue rate. The semivariance is a more plausible measure of risk (as Markowitz himself admits) and is backed by theoretical,empirical, and practical considerations. Furthermore, the semivariance is more useful than the standard variance when the underlying distribution of returns is skewed and just as useful when the underlying distribution is symmetric. In this paper, we summarize and conclude several semivariance model. On the other side, we put forward to an Multi-Period semi-variance portfolio and the Multi-Period Markowitz model in the China Stock Markets.2. CVaR Risk Measuring Practice under transaction costIn this article, we put to use the CVaR Risk Measuring norm and put forward to a new optimal portfolio under transaction cost function whatis divided into sections. By using 0-1 variables,we change this problem to nonlinear programming which contains 0-1 variables. We made empirical analysis on China stock market, which proved the validity of this model. This paper put forward to a new method for rational portfolio.