基于最小信息熵-最大增值熵的投资组合优化模型  

Portfolio optimization model based on the minimum comentropy and the maximum value-added entropy

作　　者：董雪璠 王秀国[2] 周荣喜[1] 宗泽[1] 

机构地区：[1]北京化工大学经济管理学院,北京100029 [2]中央财经大学应用数学学院,北京100081

出　　处：《北京化工大学学报（自然科学版）》2011年第6期120-124,共5页Journal of Beijing University of Chemical Technology(Natural Science Edition)

基　　金：国家自然科学基金(70901079/70701003/71171012);中央高校基本科研业务费专项资金(ZZ1017);北京化工大学学科建设项目(2010096);大学生科技创新基金项目(101001022)

摘　　要：针对Markowitz的均值-方差模型的缺陷,用信息熵代替方差度量风险,用反映资金的增值速度的增值熵代替均值,提出了一种新型投资组合模型——最小信息熵-最大增值熵模型,并通过多目标决策方法中的模糊集理论对模型进行求解。同时,给出了通过引入权重系数,将原模型转化为了具有单一目标函数的求解方法。最后通过上海证券交易所的实际数据验证了模型的可行性和有效性。In order to overcome the defects of Markowitz＇s mean-variance model,a new portfolio model has been developed.The model is based on the minimum comentropy and the maximum value-added entropy model by using comentropy to measure risk instead of variance,and making value-added entropy indicate the value-added rate of funds instead of the mean.The model can be calculated by using fuzzy set theory in a multi-objective decision-making method.A method of solving the model is also given in which the original model is translated into a single objective function through introducing a weight coefficient.The model is shown to be feasible and valid by using data from the Shanghai Stock Exchange.

关 键 词：投资组合模型 信息熵 增值熵 模糊集理论 

分 类 号：F224[经济管理—国民经济] F830.9