基于标度理论的股指时间序列相似性分析

摘要/Abstract

摘要： 股指时间序列的相似性分析是当前金融学研究的热点之一。为了提高股指时间序列相似性分析的准确度,从标度不变性、多重分形及波动聚集性三个层面定义了标度理论的度量指标,并基于此对股指序列进行表示。将分割后的每一序列子区间看作时间点,则分割、表示后的不同股指序列构成一个多指标的面板数据。基于面板数据特征及指标相对重要性,提出了一种新型的多指标面板数据相似性度量函数——复合距离函数,用以度量股指时间序列的相似性。聚类结果表明,相较于其他两种方法,基于标度理论和复合距离函数的相似性度量方法能够显著提高相似性度量的准确度,同时具有较强的稳健性。

关键词: 标度理论, 股指序列, 相似性分析, 复合距离函数, K-means算法

Abstract: Similarity analysis of stock indices time series is one of the key research contents in financial studies. In order to improve the accuracy of stock indices time series similarity analysis, we define the metrics indexes of scale theory based on scale invariance, multifractal character, and volatility clustering. Stock indices time series are represented by the three indices. If the segmentation is viewed as a time point, the stock indices time series split and expressed will constitute a multivariable panel data. Based on the features of panel data and the relative importance of these indicators, we put forward a new similarity measurement function, the complex-distance-function, to analyse the similarity of stock indices time series. Clustering results indicate that, compared with the two other methods, the similarity analysis based on scale theory and complex-distance-function can improve the accuracy of the analysis result significantly with strong robustness.

Key words: scale theory, StocR indices, similarity analysis, complex-distance-function, K-means algorithm

中图分类号:

F830

岳意定, 訚军, 柯海霞. 基于标度理论的股指时间序列相似性分析[J]. 运筹与管理, 2014, 23(5): 221-230.

YUE Yi-ding, YIN Jun, KE Hai-xia. Similarity Analysis of Stock Indices Time Series Based on Scale Theory[J]. Operations Research and Management Science, 2014, 23(5): 221-230.

参考文献

[1] Fu T. A review on time series data mining[J]. Engineering Application of Artificial Intelligence, 2011, 24: 164-181.
[2] Dong X L, Gu C K, Wang Z O. Research on shape-based time series similarity measure[C]. Proceeding of the Fifth International Conference on Machine Learning and Cybernetics, Dalian, 2006: 1253-1258.
[3] Zhang Z, Liu X Y, Wang H Q. Discovery in stock time series based on perceptually important point algorithm[C]. Proceeding of International Systems Conference, San Diego, La, USA, 2006.
[4] Fu T, Chung F L, Luk R, et al. Representing financial time series based on data point importance[J]. Engineering Applications of Artificial Intelligence, 2008, 21: 277-300.
[5] 刘懿,鲍德沛,杨泽红等.新型时间序列相似性度量方法研究[J].计算机应用研究,2007,(5):112-114.
[6] Dattasharma A, Tripathi P K, Gangadharpalli S. Identifying stock similarity based on episode distance[C]. 11th International Conference on Computer and Information Technology, Khulna, 2008: 28-35.
[7] 刘威,邵良杉,曾繁慧等.基于SAX方法的股票时间序列数据相似性度量方法研究[J].计算机工程与科学,2009,31(9):115-118.
[8] 崔靖,赵秀娟,宋吟秋.中日股价序列相似性的比较分析[J].系统工程理论与实践,2009,29(12):125-133.
[9] 倪丽萍,倪志伟.一种基于趋势分形维数的股指时间序列相似性分析方法[J].系统工程理论与实践,2012,32(9):1900-1907.
[10] Gavrilov M, Anguelov D, Indyk P, et al. Mining the stock market: which measure is best [C]. Proceeding of the KDD, Boston, Ma, USA, 2000. 487-496.
[11] Mandelbort B. The fractal geometry of nature[M]. New York: Freeman, 1982.
[12] Edgar Peter. Chaos and order in the capital markets[M]. John Wiley & Sons, Inc, 1996.
[13] Mandelbort B. Fractal and scaling in finance: discontinuity concentration, risk[M]. New York: Springer, 1998.
[14] Everetsz C J G. Fractal geometry of financial time series[J]. Fractals, 1995, 3: 609-616.
[15] Andreadis, Self-criticality and stochasticity of an S&P 500 index time series[J]. Chaos, Solitions and Fractal, 2000, 11: 1047-1059.
[16] Barabasi A, Vicsek T. Multifractality of self-affine fractals[J]. Physica A, 1991, 44: 2730-2733.
[17] Davis A, Marshak A, Wiscombe W, Cahalan R. Multifractal characterization of intermittency in nonstationary geophysical signals and fields. In: Trevino G, Harding J, Douglas B, Andreas E. Current Topics in Nonstationary Analysis. World Scientific, Singapore, 1996: 97-158.
[18] Koscielny B E, Kantelhardt J W, Braun P, et al. Long-term persistence and multifractal of river runoff records: detrended fluctuation studies[J]. Journal of Hydrology, 2006, 322: 120-137.
[19] 高红兵,潘瑾,陈宏民.深圳成份股指数收益率序列的分形维[J].预测,2000,(6):50-51.
[20] 徐绪松,陈彦斌.深沪股市分形维实证研究[J].数量经济技术经济研究,2000,(11):59- 61.
[21] 熊正丰.金融时间序列分形维估计的小波方法[J].系统工程理论与实践,2002,(12):48-53.
[22] 庄新田,黄小原.证券市场的标度理论及实证研究[J].系统工程理论与实践,2003,(3):1-9.
[23] 范英,魏一鸣.基于R/S分析的中国股票市场分形特征研究[J].系统工程,2004,22(11):46-51.
[24] 宿成建,缪晓波,刘星.中国证券市场的非线性特征与分形维分析[J].系统工程理论与实践,2005,(5):68-73.
[25] 苑莹,庄新田.金融时间序列的标度特性实证研究[J].管理工程学报,2008,(2):85- 89.
[26] 许文坤,张卫国.金融时间序列分形维参数估计方法比较及应用[J].系统工程,2011,29(7):11-18.
[27] 何建敏,常松.中国股票市场多重分形游走及其预测[J].中国管理科学,2002,10(3):11-17.
[28] 胡雪明,宋学峰.深沪股票市场的多重分形分析[J].数量经济技术经济研究,2003,(8):124-127.
[29] 吴文峰,黄登仕,吴冲锋.中国股票市场的多标度特征[J].数量经济技术经济研究,2003,(9):112-115.
[30] 卢方元.中国股票市场收益率的多重分形分析[J].系统工程理论与实践,2004,(6):50-54.
[31] 施锡铨,艾克风.股票市场风险的多重分形分析[J].统计研究,2004,(9):33-36.
[32] 苑莹,庄新田,金秀.基于MF-DFA的中国股票市场多标度特性及成因分析[J].管理工程学报, 2009,(4):96-99.
[33] Gopikrishnan P, Plerou V, Liu Y, et al. Scaling and correlation in financial data[J]. Physica A, 2000, 287: 362-373.
[34] Last M, Klein Y. Knowledge discovery in time series databases[J]. IEEE Trans on System Man and Cybernetics-part b, 2001, 31(1): 160-169.
[35] Edger E P. Chaos and order in the capital market[M]. Economic Science Press, 1999: 64- 83.
[36] Andreadis J, Serletis A. Evidence of a random multifractal turbulent structure in the dow jones industrial average[J]. Chaos, Solitions and Fractals, 2002, 13: 1309-1315.
[37] Kantelhardt J W, Zschiegner S A, Koscielny-Bunde E. Multifractal detrended fluctuation analysis of nonstationary time series[J]. Physica A, 2002, 316(1- 4): 87-114.
[38] Bonzo D C, Hennoeilla A Y. Clustering panel data via perturbed adaptive simulated annealing and genetic algorithms[J]. Advances in Complex System, 2004, 4: 339-360.
[39] Ren J, Shi S L. Multivariable panel data ordinal clustering and its application in competitive strategy identification of appliance-wiring listed companies[C]. International Conference on Management Science & Engineering(16th), Moscow, Russia, 2009: 253-258.
[40] 朱建平,陈民恳.面板数据的聚类分析及其应用[J].统计研究,2007,24(4):11-14.
[41] 郑兵云.多指标面板数据的聚类分析及其应用[J].数理统计与管理,2008,27(2):265-270.
[42] 陈可,刘思峰.灰色关联度在面板数据中的拓展及应用[J].系统工程理论与实践,2010,30(7):1253-1259.
[43] 李因果,何晓群.面板数据聚类方法及应用[J].统计研究,2010,27(9):73-77.
[44] 黄德才,李秉焱.AHP群决策的几何平均超传递近似法[J].控制与决策,2012,(5):797- 800.