在包含不确定性的投资组合策略研究中，对不同权重估计量进行加权能够对冲估计误差，从而取得更好的样本外效果.一般来说，这类策略的加权权重往往取决于一定的分布假设，在实际应用中具有比较大的局限性.为了改进这一点，本文使用多任务相关学习（multi-task relationship learning，MTRL）的算法框架，通过估计全局方差最小（global minimum variance，GMV）和均值-方差（mean-variance，MV）切点组合权重之间的相关性矩阵，对GMV和MV切点组合的权重进行了同步估计，从而实现了加权估计的类似效果.在实证检验方面，本文使用A股2000年至2019年的全样本日数据，构建了两个数据集：因子组合以及从沪深300指数成分股中随机抽取的个股组合.基于因子组合数据集的样本外结果，本文发现基于MTRL的MV切点策略（MTRL-MV）能够在夏普率，标准差和换手率上取得显著优于原MV切点组合策略，等权重以及其他几种加权策略的表现.最后，本文使用A股的因子组合子样本、随机抽样的个股组合以及美股因子组合共3个数据集进行了稳健性检验，结果表明MTRL-MV相对于基准策略MV具有比较显著的提升.
Abstract
Among all the portfolio optimization studies that consider uncertainty, it has been shown that by combining different strategies, estimation error can be hedged and better out-of-sample performance can be achieved. In general, these kinds of combining strategies rely heavily on the distribution assumption to decide the combining weights, which may weaken their practical applicability. To improve this, this paper utilizes multi-task relationship learning (MTRL) framework to estimate global minimum variance (GMV) weight and mean-variance (MV) tangency weight simultaneously, by estimating the correlation matrix between these two weights, achieving a combining-like result. In terms of empirical tests, this paper uses daily data of A-share market spanning from 2000 to 2019 to construct two datasets:factor portfolios and stock portfolios randomly collected from HS300 index constituents. The empirical out-of-sample result based on factor portfolio dataset suggests that MTRL-MV can achieve better performance than original MV, equally-weighted (EW) and other combining strategies in terms of Sharpe ratio, standard deviation and turnover. In the end, this paper uses three datasets:The subsample of factor portfolios from Chinese A share and US stock market and individual stock portfolios, to conduct robustness test, which confirms MTRL-MV's improvement compared to other strategies.
关键词
投资组合优化 /
加权估计 /
多任务相关学习
{{custom_keyword}} /
Key words
portfolio optimization /
combining estimation /
multi-task relationship learning
{{custom_keyword}} /
中图分类号：
F830.9
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Markowitz H. Portfolio selection[J]. The Journal of Finance, 1952, 7(1):77-91.
[2] 倪宣明, 钱龙, 赵慧敏, 等. 高频数据下高维协方差阵的RCM算法估计与应用[J]. 系统工程理论与实践, 2019, 39(8):1943-1953.Ni X M, Qian L, Zhao H M, et al. Large-dimensional covariance matrix estimation and its application with RCM using high frequency data[J]. Systems Engineering-Theory & Practice, 2019, 39(8):1943-1953.
[3] Merton R C. On estimating the expected return on the market:An exploratory investigation[J]. Journal of Financial Economics, 1980, 8(4):323-361.
[4] Best M J, Grauer R R. On the sensitivity of mean-variance-efficient portfolios to changes in asset means:Some analytical and computational results[J]. The Review of Financial Studies, 1991, 4(2):315-342.
[5] Michaud R O. The Markowitz optimization enigma:Is ‘optimized’ optimal?[J]. Financial Analysts Journal, 1989, 45(1):31-42.
[6] Green R C, Hollifield B. When will mean-variance efficient portfolios be well diversified?[J]. The Journal of Finance, 1992, 47(5):1785-1809.
[7] Demiguel V, Garlappi L, Uppal R. Optimal versus naive diversification:How inefficient is the 1/N portfolio strategy?[J]. The Review of Financial studies, 2007, 22(5):1915-1953.
[8] Demiguel V, Garlappi L, Nogales F J, et al. A generalized approach to portfolio optimization:Improving performance by constraining portfolio norms[J]. Management Science, 2009, 55(5):798-812.
[9] Jagannathan R, Ma T. Risk reduction in large portfolios:Why imposing the wrong constraints helps[J]. The Journal of Finance, 2003, 58(4):1651-1683.
[10] Ledoit O, Wolf M. Honey, I shrunk the sample covariance matrix[J]. The Journal of Portfolio Management, 2004, 30(4):110-119.
[11] Kan R, Zhou G. Optimal portfolio choice with parameter uncertainty[J]. Journal of Financial and Quantitative Analysis, 2007, 42(3):621-656.
[12] Tu J, Zhou G. Markowitz meets Talmud:A combination of sophisticated and naive diversification strategies[J]. Journal of Financial Economics, 2011, 99(1):204-215.
[13] Jiang C, Du J, An Y. Combining the minimum-variance and equally-weighted portfolios:Can portfolio performance be improved?[J]. Economic Modelling, 2019, 80:260-274.
[14] 黄琼, 朱书尚, 姚京. 投资组合策略的有效性检验:基于中国市场的实证分析[J]. 管理评论, 2011, 23(7):3-10+33.Huang Q, Zhu S S, Yao J. Investment efficiency of oortfolio strategies:An empirical study in China[J]. Management Review, 2011, 23(7):3-10+33.
[15] 吴文生, 韩其恒, 曹志广. 基于数据窥查效应下资产配置有效性的评估研究[J]. 系统工程理论与实践, 2018, 38(11):2762-2775.Wu W S, Han Q H, Cao Z G. Data snooping bias in the performance evaluation of asset allocation strategies[J]. Systems Engineering-Theory & Practice, 2018, 38(11):2762-2775.
[16] Zhang Y, Yeung D-Y. A regularization approach to learning task relationships in multitask learning[J]. ACM Transactions on Knowledge Discovery from Data (TKDD), 2014, 8(3):12.
[17] Fan J, Zhang J, Yu K. Vast portfolio selection with gross-exposure constraints[J]. Journal of the American Statistical Association, 2012, 107(498):592-606.
[18] Britten-Jones M. The sampling error in estimates of mean-variance efficient portfolio weights[J]. The Journal of Finance, 1999, 54(2):655-671.
[19] Ao M, Li Y, Zheng X. Approaching mean-variance efficiency for large portfolios[J]. The Review of Financial Studies, 2019, 32(7):2890-2919.
[20] Ledoit O, Wolf M. Nonlinear shrinkage of the covariance matrix for portfolio selection:Markowitz meets Goldilocks[J]. The Review of Financial Studies, 2017, 30(12):4349-4388.
[21] Fan J, Li Y, Yu K. Vast volatility matrix estimation using high-frequency data for portfolio selection[J]. Journal of the American Statistical Association, 2012, 107(497):412-428.
[22] Jorion P. Bayes-Stein estimation for portfolio analysis[J]. Journal of Financial and Quantitative Analysis, 1986, 21(3):279-292.
[23] Fama E F, French K R. Common risk factors in the returns on stocks and bonds[J]. Journal of Financial Economics, 1993, 33(1):3-56.
[24] Shi F, Shu L, Yang A, et al. Improving minimum-variance portfolios by alleviating overdispersion of eigenvalues[J]. Journal of Financial and Quantitative Analysis, 2020, 55(8):2700-2731.
[25] Jobson J D, Korkie B M. Performance hypothesis testing with the Sharpe and Treynor measures[J]. The Journal of Finance, 1981, 36(4):889-908.
[26] 黄嵩, 倪宣明, 钱龙, 等. 基于集成学习的在线高维投资组合策略[J]. 系统科学与数学, 2020, 40(1):29-40.Huang S, Ni X M, Qian L, et al. Large-dimensional online portfolio strategy based on ensemble learning[J]. Journal of Systems Science & Mathematical Science, 2020, 40(1):29-40.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金（71991474）
{{custom_fund}}
PDF(748 KB)
