证券市场的动态网络模型构建与演化规律研究  

Dynamic Network Model Construction and Evolution Exploration in Financial Markets

作　　者：韩华[1] 刘婉璐[1] 汪金水[1] 

机构地区：[1]武汉理工大学理学院

出　　处：《管理学报》2013年第2期299-304,共6页Chinese Journal of Management

基　　金：国家自然科学基金资助项目(71140015);中央高校基本科研业务费专项基金资助项目(2011-1a-034)

摘　　要：为分析证券市场的演化规律,提出了动态网络模型构建与拓扑结构分析方法。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,采用边权重过滤技术建立了证券市场的动态网络模型,并从网络的基本特征和社团结构探索证券市场的演化规律。通过计算发现,上海证券网络个体之间的平均相关性和聚集程度基本稳定,连通性则呈现增强的趋势。利用加权CNM算法对该动态网络进行社团结构划分,发现网络的最优模块度Q值呈现增大的趋势,这表明该网络的社团结构越来越明显。按行业对这些主要社团进一步分析发现:制造业是整个网络最核心的行业,其次是批发和零售贸易等5个行业。该证券动态网络的建模与演化规律分析方法可以推广到一般复杂网络理论之中。In order to analyze the evolution of financial markets, the problem of dynamic network model construction and topology analysis s proposed. We use the daily closing prices of portfolio com- prising of 884 A share stocks traded in the Shanghai Stock Exchange in the period 2000-2011 and es- timate financial networks where nodes correspond to stocks and edges correspond to none vanishing correlation coefficients. Then we use the weighted edge filter technology to build a dynamic network model of financial markets, and analyze the network＇s basic characteristics and community structures to explore the evolution of financial markets. The degree distribution of the dynamic financial network has a power law form, and keeps stable except the connectivity shows a trend of stronger. We use the weighted CNM algorithm to detect community structure of the dynamic network, it can be found that the modularity Q become larger over the time, which showed a strong community structure develop- ment. e further analyze these communities by their industry classification, and it can be revealed that manufacturing is the core of the network industry, followed by wholesale and retail trade of the five industries. The financial dynamic network modeling and analysis of evolution can be extended to the general theory of complex networks.

关 键 词：证券网络 演化规律 社团结构 加权CNM算法 

分 类 号：C93[经济管理—管理学] N949[自然科学总论—系统科学]