基于改进Black-Litterman模型的投资组合优化  

Portfolio Optimization Based on an Improved Black-Litterman Model

作　　者：黄羿[1] 蒋文正 HUANG Yi;JIANG Wenzheng(College of Mathematics and Statistics,Jishou University,Jishou 416000,Hunan China)

机构地区：[1]吉首大学数学与统计学院,湖南吉首416000

出　　处：《吉首大学学报（自然科学版）》2024年第2期89-96,共8页Journal of Jishou University(Natural Sciences Edition)

基　　金：湖南省教育厅青年项目(22B0522);国家级大学生创新创业训练计划项目(202210531004)。

摘　　要：考虑到金融市场“非完全有效性”且投资者“非完全理性”,通过贝叶斯框架建立了投资者观点与多渠道信息相结合的改进Black-Litterman模型,由此确定了最优的个性化投资策略.在中国股票市场的实证研究中,利用SVM-ARIMA-GARCH模型解决了投资者观点量化的问题.对比几类参考策略,改进Black-Litterman模型所确定的最优投资策略的样本外绩效表现更加稳健,在不同市场行情下均能获得较高的夏普比率和较低的换手率.For the"imperfect effectiveness"of financial markets and the"imperfect rationality"of investors,an improved Black-Litterman model combining investor views and multi-channel information is developed by means of the Bayesian framework to determine the optimal personalized investment strategies.In an empirical study of the Chinese stock market,the problem of quantifying investor views is addressed using the SVM-ARIMA-GARCH model.Compared with several reference strategies,the optimal investment strategy identified by the improved Black-Litterman model has a more robust out-of-sample performance,with higher Sharpe ratios and lower turnover ratios in different market conditions.

关 键 词：BLACK-LITTERMAN模型 贝叶斯框架 投资者观点 投资组合优化 

分 类 号：F830.9[经济管理—金融学]