基于可信性均值-方差-偏度-正弦熵的投资组合模型

发布时间：2017-12-26 19:12

本文关键词：基于可信性均值-方差-偏度-正弦熵的投资组合模型　出处：《北京化工大学学报(自然科学版)》2017年02期 　论文类型：期刊论文

【摘要】：通过引入可信性理论和偏度约束,分别建立了同时满足随机不确定和模糊不确定情形的均值-方差-偏度-正弦熵多目标投资组合优化模型(Mult-M-V-S-SE)和含有收益及风险系数的单目标投资组合优化模型(M-V-SSE);然后运用马尔科夫方法预测模糊收益率,利用遗传算法优化模型投资策略,通过上海证券交易所数据进行实证比较。结果表明:Mult-M-V-S-SE和M-V-S-SE两模型效果均超过均匀投资策略(MEAN);M-V-S-SE模型灵活且稳定,更具有优势,在满足投资者需求的同时可实现更高的累计收益。
[Abstract]:Through the introduction of credibility theory and skewness constraints, are established at the same time satisfy the random uncertainty and fuzzy uncertainty of the mean variance skewness sine entropy multi-objective portfolio optimization model (Mult-M-V-S-SE) and single target investment contains profit and risk coefficient of the combination optimization model (M-V-SSE); and then use the Markov forecast method of Fuzzy income the rate of using genetic algorithm to optimize the model, investment strategy, compare the empirical data through the Shanghai stock exchange. The results show that the Mult-M-V-S-SE and M-V-S-SE two models both surpass the even investment strategy (MEAN), and the M-V-S-SE model is flexible and stable, and has more advantages. It can achieve higher accumulated income while meeting the needs of investors.
【作者单位】：北京化工大学经济管理学院;对外经济贸易大学金融学院;
【基金】：国家自然科学基金(71631005) 教育部人文社会科学研究规划基金(16YJA630078)
【分类号】：F224;F832.39
【正文快照】： 引言现代投资组合理论在Markowitz[1]的均值方差模型基础上取得长足发展,但是该模型存在极端假设、高收益惩罚和协方差矩阵复杂等缺陷。后续学者在这一领域展开了深入探究[2-5],相继提出半方差、绝对离差、半绝对离差和VAR等工具以克服均值方差模型的局限性。本课题组对不同风

【相似文献】