基于微分进化算法的多阶段投资组合优化

投资组合优化问题就是决定每个具有特定风险和回报的投资资产在总投资价值中的分配比例。在不断变化的金融市场中,多阶段投资组合优化就是通过周期性重新平衡投资资产比例管理投资组合以达到投资风险最小或投资回报最大。研究了基于微分进化算法在多阶段投资组合优化中制定投资决策的方法,目标函数是最大化个人经济效益或最大化周期结束时个人财富。通过比较用微分进化算法和遗传算法(GA)优化同样的资产对象所得到的期望收益率均值与方差,该文所提出的方法的优越性被美国标准普尔指数100的不同股票和现金分配优化所证实。

Multi-stage portfolio optimization using differentiation evolution algorithms

Portfolio optimization problem decides the percentage of the overall portfolio value allocated to each portfolio component with specified risk-return characteristics.A multistage optimization manages portfolio in constantly changing financial markets by periodically rebalancing the asset portfolio to achieve return maximization and/or risk minimization.This paper purpose is to study the method of decision-making in the field of multi-stage portfolio optimization using Differentiation Evolution Algorithms.The objective function is to maximize one's economic utility or end-of-period wealth.This paper introduces how to use Differentiation Evolution Algorithms to find best portfolio according to objective function.By comparing the expect return and their variances that come from optimizing the allocation of cash and various stocks in the market of USA using Differentiation Evolution Algorithms with Genetic Algorithms,the performance of this method is demonstrated.