股票遴选与投资业绩——基于属性约简及动态时间规整距离

管理评论 ›› 2023, Vol. 35 ›› Issue (4): 55-65.

股票遴选与投资业绩——基于属性约简及动态时间规整距离

巩建英¹, 南梦佳², 李郝峰³, 吉小东⁴

1. 中国科学院大学经济与管理学院, 北京 100190;
2. 邯郸银行股份有限公司石家庄分行, 石家庄 050010;
3. 中原银行股份有限公司, 郑州 450046;
4. 河北师范大学商学院, 石家庄 050024

收稿日期:2020-10-10 出版日期:2023-04-28 发布日期:2023-06-01
通讯作者: 吉小东(通讯作者),河北师范大学商学院教授,硕士生导师,博士。
作者简介:巩建英,中国科学院大学经济与管理学院博士研究生;南梦佳,邯郸银行股份有限公司石家庄分行职员,硕士;李郝峰,中原银行股份有限公司数据建模师,硕士。
基金资助:
国家自然科学基金项目(71571062)；全国统计科学研究重点项目(2019LZ17)

The Selection of Risky Assets and Investment Performance Based on Attribute Reduction and Dynamic Time Warping Distances

Gong Jianying¹, Nan Mengjia², Li Haofeng³, Ji Xiaodong⁴

1. School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190;
2. Shijiazhuang Branch, Bank of Handan, Shijiazhuang 050010;
3. Zhongyuan Bank, Zhengzhou 450046;
4. College of Business, Hebei Normal University, Shijiazhuang 050024

Received:2020-10-10 Online:2023-04-28 Published:2023-06-01

摘要/Abstract

摘要： 评价风险资产价值的指标（属性）有很多，以少量指标（属性）从数以千计的风险资产中筛选出有投资价值的资产对投资业绩影响重大。本文以股票市场为例，提出了基于属性约简及动态时间规整距离的股票遴选方法。首先利用基于属性重复度的改进属性约简算法筛选出能区分股票投资价值的约简属性集，之后将单指标动态时间规整算法拓展到多指标，建立股票间基于约简属性集的多维动态时间规整距离集，利用聚类技术对规整距离集进行聚类并通过拆分规整距离对股票进行类别划分，遴选收益-风险特征均较好的类别中的股票构建资产池。数值试验表明：随机模拟权重和均等权重投资组合的累积收益率均高于市场基准，且资产的优化配置进一步改善了投资组合的收益-风险特征。该方法通过属性约简降低了投资者评价股票投资价值的难度，通过多维动态时间规整距离度量了不同股票关于各指标（属性）时间序列变动趋势的相似程度；遴选过程基于历史数据，避免了主观因素的影响，且筛选结果具有稳健性。此外，该方法适合于一般风险资产的遴选，还可以将不同市场不同行业考虑在内，以便更好地实现分散化投资。

关键词: 属性约简, 属性重复度, 动态时间规整距离, 变动趋势相似性, 聚类

Abstract: There are a variety of indices (attributes) to evaluate the investment value of risky assets. It is vital for investors to assess their investment values of risky assets based on less indices. Taking stock market as an exmple, this paper proposes a stock-choosing approach that is based on attribute reduction and dynamic time warping distances. First an improved algorithm based on overlap ratio of attributes is proposed to pick out less attributes to evaluate stocks’ values. Then single-index dynamic time warping algorithm is extended to multiple indices and a set of dynamic time warping distances between stocks is computed based on reduced attributes. These distances are clustered and partitioned to match individual stocks into categories, and then the categoroies with better return-risk performance are chosen to construct the asset pool. Numerical experiment validates that the cumulative returns of both random-weight and equal-weight portfolio have better return than market benchmark, and the optimal allocation of assets improves the characteristics of returns and risks. This approach reduces the difficulties for investors to evaluate the stocks’ values via reduced attributes and measures the similarities between the trends of times series related to these indices by multi-index dynamic time warping distances. The procedure to choose risky assets is based on actual data, which avoids the influences of subjective factors and obtains robust assets pool. The proposed approach is suitable for the selection of general risky assets and is helpful for diversified investment if different markets and industries are taken into consideration.

Key words: attribute reduction, overlap ratio of attribute, dynamic time warping distance, similarity of tracks, cluster

巩建英, 南梦佳, 李郝峰, 吉小东. 股票遴选与投资业绩——基于属性约简及动态时间规整距离[J]. 管理评论, 2023, 35(4): 55-65.

Gong Jianying, Nan Mengjia, Li Haofeng, Ji Xiaodong. The Selection of Risky Assets and Investment Performance Based on Attribute Reduction and Dynamic Time Warping Distances[J]. Management Review, 2023, 35(4): 55-65.

参考文献

[1] Swensen D. F. Unconventional Success:A Fundamental Approach to Personal Investment[M]. Massachusetts:Free Press, 2005
[2] Malkiel B. G. A Random Walk down Wall Street:Including a Life-Cycle Guide to Personal Investing[M]. New York:W. W. Norton Company, 1996
[3] Wang Y. M., Ma J. P. Excess Volatility and the Cross-Section of Stock Returns[J]. North American Journal of Economics and Finance, 2014,27(C):1-16
[4] 王翠香,刘蕾.层次分析法在选股决策中的应用[J].数学的理论与实践, 2008,38(17):42-48
[5] 王艳,陈敏,赵子龙.基于高频夏普指数的组合证券投资模型[J].系统工程理论与实践, 2015,35(1):17-25
[6] Levin A. U. Stock Selection via Nonlinear Multi-factor Models[C]. Advances in Neural Information Processing Systems 8, 1996
[7] Fan A., Palaniswami M. Stock Selection Using Support Vector Machines[C]. International Joint Conference on Neural Networks, 2001
[8] Hart J. V. D., Slagter E., Dijk D. V. Stock Selection Strategies in Emerging Markets[J]. Journal of Empirical Finance, 2003,10(1-2):105-132
[9] Rouwenhorst K. G. International Momentum Strategies[J]. The Journal of Finance, 1998,53(1):267-284
[10] Griffin J. M., Ji X. Q., Martin J. S. Momentum Investing and Business Cycle Risk:Evidence from Pole to Pole[J]. The Journal of Finance, 2003,58(6):2515-2547
[11] Rachev S., Jasic T., Stoyanov S., et al. Momentum Strategies Based on Reward-Risk Stock Selection Criteria[J]. Journal of Banking and Finance, 2007,31(8):2325-2346
[12] Daniel K., Moskowitz T. J. Momentum Crashes[R]. NBER Working Paper 20439, 2014
[13] Daniel K., Jagannathan R., Kim S. Tail Risk in Momentum Strategy Returns[R]. NBER Working Paper 18169, 2012
[14] Wong S. K. M., Ziarko W. On Optimal Decision Rules in Decision Tables[J]. Bulletin of the Polish Academy of Sciences, 1985,33(11-12):693-696
[15] 苗夺谦,王钰.粗糙集理论中概念与运算的信息表示[J].软件学报, 1999,10(2):113-116
[16] 吴尚智,苟平章.粗糙集和信息熵的属性约简算法及其应用[J].计算机工程, 2011,37(7):56-58
[17] Skowron A., Rauszer C. The Discernibility Matrices and Functions in Information Systems[C]//Proc of Intelligent Decision Support:Handbook of Applications and Advances of the Rough Sets Theory. Dordrecht:Kluwer Academic Publishers, 1992
[18] Pawlak Z. Rough Sets[J]. International Journal of Computer and Information Sciences, 1982,11(5):341-356
[19] Nguyen S. H. Some Efficient Algorithms for Rough Set Methods[C]. The 6th International Conference of Information Processing and Management of Uncertainty in Knowledge-based Systems, 1996
[20] 陈鑫影,李冠宇,刘彦含.基于决策依赖度的粗糙集约简模型研究[J].系统工程理论与实践, 2016,36(2):505-516
[21] 葛浩,李龙澍,杨传健.基于相对分辨能力的属性约简算法[J].系统工程理论与实践, 2015,35(6):1595-1603
[22] Liu H., Hussain F., Tan C. L., et al. Discretization:An Enabling Technique[J]. Data Mining and Knowledge Discovery, 2002,6:393-423
[23] Aleksander Ø. Discernibility and Rough Sets in Medicine:Tools and Applications[D]. Trondheim:Norwegian University of Science and Technology, Ph.D. Dissertation, 1999
[24] 侯利娟,王国胤,聂能,等.粗糙集理论中的离散化问题[J].计算机科学, 2000,27(12):89-94
[25] 刘甲伟.基于粗糙集的绩优股票预测系统研究[D].大连交通大学硕士学位论文, 2009
[26] Itakura F. Minimum Prediction Residual Principle Applied to Speech Recognition[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1975,23(1):67-72
[27] Berndt D. J., Clifford J. Using Dynamic Time Warping to Find Patterns in Time Series[R]. AAAI-94 Workshop on Knowledge Discovery in Databases, Washington, 1994
[28] 刘云霞.基于动态时间规整的面板数据聚类方法研究及应用[J].统计研究, 2016,33(11):93-101
[29] 冯钧,陈焕霖,唐志贤,等.一种基于DTW的新型股市时间序列相似性度量方法[J].数据采集与处理, 2015,30(1):99-105
[30] Rockafellar R. T., Uryasev S. Conditional Value-at-Risk for General Loss Distributions[J]. Journal of Banking and Finance, 2002,26(7):1443-1471
[31] 陈国进,许秀,赵向琴.罕见灾难风险和股市收益--基于我国个股横截面尾部风险的实证分析[J].系统工程理论与实践, 2015,35(9):2186-2199
[32] 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