Compositional segmentation and complexity measurement in stock indices

In this paper, we introduce a complexity measure based on the entropic segmentation called sequence compositional complexity (SCC) into the analysis of financial time series. SCC was first used to deal directly with the complex heterogeneity in nonstationary DNA sequences. We already know that SCC was found to be higher in sequences with long-range correlation than those with low long-range correlation, especially in the DNA sequences. Now, we introduce this method into financial index data, subsequently, we find that the values of SCC of some mature stock indices, such as S&P500 (simplified with S&P in the following) and HSI, are likely to be lower than the SCC value of Chinese index data (such as SSE). What is more, we find that, if we classify the indices with the method of SCC, the financial market of Hong Kong has more similarities with mature foreign markets than Chinese ones. So we believe that a good correspondence is found between the SCC of the index sequence and the complexity of the market involved.

[1]  J. Stein,et al.  A Unified Theory of Underreaction, Momentum Trading and Overreaction in Asset Markets , 1997 .

[2]  Pengjian Shang,et al.  Detecting long-range correlations of traffic time series with multifractal detrended fluctuation analysis , 2008 .

[3]  Jan W. Kantelhardt.  Fractal and Multifractal Time Series , 2009, Encyclopedia of Complexity and Systems Science.

[4]  Masaki Aono,et al.  Time Series Data Mining for Multimodal Bio-Signal Data , 2006 .

[5]  J. Oliver,et al.  Sequence Compositional Complexity of DNA through an Entropic Segmentation Method , 1998 .

[6]  P. Bernaola-Galván,et al.  Compositional segmentation and long-range fractal correlations in DNA sequences. , 1996, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[7]  A. V. Coronado,et al.  Segmentation of time series with long-range fractal correlations , 2012, The European physical journal. B.

[8]  Akihiro Sato,et al.  A Comprehensive Analysis of Time Series Segmentation on Japanese Stock Prices , 2012, 1205.0332.

[9]  Jing Wang,et al.  Segmented inner composition alignment to detect coupling of different subsystems , 2014 .

[10]  S. S. Wilks.  The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses , 1938 .

[11]  A. Carbone,et al.  Cross-correlation of long-range correlated series , 2008, 0804.2064.

[12]  Jing Wang,et al.  MULTIFRACTAL CROSS-CORRELATION ANALYSIS BASED ON STATISTICAL MOMENTS , 2012 .

[13]  Pengjian Shang,et al.  Chaotic SVD method for minimizing the effect of exponential trends in detrended fluctuation analysis , 2009 .

[14]  Ingoo Han,et al.  Application of a hybrid genetic algorithm and neural network approach in activity-based costing , 2003, Expert Syst. Appl..

[15]  H. Stanley,et al.  Cross-correlations between volume change and price change , 2009, Proceedings of the National Academy of Sciences.

[16]  S. Havlin,et al.  Detecting long-range correlations with detrended fluctuation analysis , 2001, cond-mat/0102214.

[17]  Hua-Ning Hao.  Notice of RetractionShort-term forecasting of stock price based on genetic-neural network , 2010, 2010 Sixth International Conference on Natural Computation.

[18]  Segmentation analysis on a multivariate time series of the foreign exchange rates , 2012, 1205.0336.

[19]  Siew Ann Cheong,et al.  The Japanese Economy in Crises: A Time Series Segmentation Study , 2012 .

[20]  Siew Ann Cheong,et al.  Will the US economy recover in 2010? A minimal spanning tree study , 2010, 1009.5800.