基于投资者观点的鲁棒性投资组合选择模型  

A Robust Portfolio Selection Model Based on Investor’s Views

作　　者：赵大萍 柏林[2] 房勇[2,3] 汪寿阳 ZHAO Da-ping;BAI Lin;FANG Yong;WANG Shou-yang(School of Finance,Capital University of Economics and Business,Beijing100070,China;Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China;School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]首都经济贸易大学金融学院,北京100070 [2]中国科学院数学与系统科学研究院,北京100190 [3]中国科学院大学经济与管理学院,北京100190

出　　处：《中国管理科学》2022年第9期1-9,共9页Chinese Journal of Management Science

基　　金：国家自然科学基金资助项目(71701138,71631008)。

摘　　要：Black-Litterman模型因其将投资者观点和市场均衡收益率结合分析的特点广受关注和应用,本文从均衡收益率和投资者观点的不确定性及参数的不确定性两方面对该模型进行鲁棒性建模。首先,本文对于投资者观点及资产均衡收益率进行鲁棒性建模,进而对资本市场均衡收益率进行深度分析,其次对风险厌恶系数进行鲁棒性建模,并基于运筹学理论将模型转化为有成熟算法的二阶锥规划问题。最后基于实际数据给出数值算例,佐证了模型的有效性。As an improvement of mean variance model, Black-Litterman model is one of the most popular methods in asset allocation. An analytical framework is provided that combines the investors’ expectation of the market with the market equilibrium rate of return, and several problems of the mean variance model are solved, such as lack of dispersion, high sensitivity to parameters, and so on. Therefore, Black-Litterman has been widely concerned by the academic community, and has achieved good results in practical application.The robustness modeling of Black-Litterman model is the main subject in this paper. The uncertainty of the model mainly comes from two aspects: one is the uncertainty of equilibrium yield and investor’sviews;the other is the uncertainty of parameters in the model. In this paper, a robust Black-Litterman model is firstly built based on the uncertainty of investor view and market equilibrium return, and an in-depth analysis of the market equilibrium return is shown. Secondly, a robust Black-Litterman model is constructed based on the uncertainty of risk aversion parameter. Because the robust portfolio selection model is often a minimax optimization problem, and the minimax optimization problem is difficult to solve, the proposed model is transformed into a second-order cone programming problem and it is solved with the mature algorithm.At last, in the numerical example, a portfolio including the assets of the United States, the United Kingdom, Germany, Japan and China is constructed. The index prices of stocks and bonds are used to describe the return of each asset, and the frequency is monthly.The results show that the annualreturns of Black-Litterman model and two robust optimization models without considering robustness are much higher than those of market portfolio and Mean-Variance model. The annual returns of two robust optimization models are slightly lower than that of ordinary Black-Litterman model, but their Sharpe Ratios are higher.In summary, Black-Litterman model is widely concerned beca

关 键 词：投资者观点 BLACK-LITTERMAN模型 鲁棒性投资组合 

分 类 号：F830.2[经济管理—金融学]