股票市场网络的模体及投资者购买行为研究

Motifs in Stock Network and Purchasing Behavior of Investors

从投资者购买股票的角度,基于模体来研究股票网络。收集2000—2011年在上海证券交易所上市的884家A股公司的收盘价格数据,建立了股票网络模型,选取rand-ESU算法检测出股票网络中的模体结构,发现模体是网络中重要的结构,通过对模体的分析,研究了购买股票的可能性,定义了投资者购买股票的可能性公式,在研究网络模体统计特征的基础上,可找到网络的控制点,对股票市场的发展状况做出评价。

The stock network was studied based on motifs from the point of view of the purchasing behavior of investors. The daily clothing prices of portfolio comprising of 884 A-share stocks traded in the Shanghai Stock Exchange in the period 2000- 2011 was used to estimate stock networks where nodes were corresponding to stocks and edges were corresponding to none vanishing correlation coefficients. A stock network model was then built. The rand-ESU algorithm was selected to detect the motifs in the stock network. It was found that motifs were important structures in networks. Then a stock purchasability function was defined for motifs that would indicate the probability of stock being purchased by the investors.