基于差异网络的关键股票动态分析

Dynamic Analysis of Influential Stocks Based on Differential Networks

股票市场的时间演化特征是一个基本而具有挑战性的问题。迄今为止,有关分析市场动态的文献都集中在预测能力较弱的宏观指标上。本文从微观的角度来探讨这一问题。在给定研究区间的情况下,首先利用滑动窗口方法和股票相关性显著性检验构造了股票网络序列。然后,生成4个差异网络。最后,从每个差异网络中识别出有影响力的股票和相应的板块,并在此基础上进行纵向分析来描述市场的演化。将上述框架应用于2006年1月至2010年4月的标准普尔500指数股票,再现了2008年的金融危机的扩散过程。

Characterizing temporal evolution of stock markets is a fundamental and challenging problem. The literature on analyzing the dynamics of the markets has focused so far on macro measures with less predictive power. This paper addresses this issue from a micro point of view. Given an investigating period, a series of stock networks are constructed first by the moving-window method and the significance test of stock correlations. Then, we generated four differential networks. Finally, influential stocks and corresponding sectors are identified from each differential network, based on which the longitudinal analysis is performed to describe the evolution of the market. The application of the above procedure to stocks belonging to Standard &Pool’s 500 Index from January 2006 to April 2010 recovers the 2008 financial crisis from the evolutionary perspective.