The Research Of Portfolio Optimization Model Based On Improved CVaR

In 1997, with the outbreak of the Asian financial crisis, the world financial turmoil began exacerbate. Especially in October 1998, the long-term capital management companies incident happened, this from the Wall Street elite, government officials and former Financial Nobel Laureate in economics, as the composition of the financial industry giant, could not escape the impact of catastrophe. This makes the financial sector began alert, people begin to study further on risk prevention and risk management issues.The main topic of this article is "The Research of optimization Portfolio based on improved CVaR". Firstly, we explain the reason why we chose this thesis and the background of it. Secondly, we discuss some very important theory about risk measurement and management, such as Mean-Variance(MV) Model, Mean-Value-at-risk(VaR) model and Mean-Conditional-Value-at-risk(CVaR) modal. The focus of this paper (Chapter 3) is a study about CVaR portfolio optimization model, risk is measured using CVaR, income is measured using mean, on this basis, we establish the following two models: one is the income of not less than a given value, minimize the risk, we establish mean - CVaR model; The other is the risk of not more than a given value, maximize the income, establish the investment portfolio optimization model with CVaR constraints. In the fourth chapter of this paper, we propose a Worst—Case CVaR method, on the assumption that the distribution conditions can be further relaxed, this method is a important improvement and added to the CVaR method. For the portfolio with uncertain exit time, we can not solve them with the common CVaR, in the last of this paper, we propose a Weighting-CVaR method to solve this condition, and we set up two models: mean - Weighted-CVaR model and the portfolio optimization model with Weighted-CVaR Constraints.