股灾前后中小板上市公司网络结构对比研究——基于最小生成树和聚类分析方法

The Study of Small and Medium Sized Listing Corporation Network Structure

2014—2016年,中国A股市场先后经历了牛市和熊市,研究这段时期中小板企业的结构性质对于分析中国中小企业有着特殊的意义。通过选取中小板流通市值前60的股票,将2014年10月30日到2016年2月19日的股票周收益率作为研究数据,用最小生成树和社区网络方法构建股票的社区结构图,选出连接更多邻点,有重要地位的"明星"股票。之后再用K-means聚类方法对股票重新分类,研究类别中成员较少的边缘类股票。最后将牛市和熊市的异同点进行对比,对其包含的经济问题进行分析。

From the year 2014 to 2016,China＇s A-share market has experienced a bull market and a bear market. Analyzing the structure of Small and medium enterprise board in this period has a special significance in studying the small and medium-sized enterprises. This article selected the date of stock return rate from October 30,2014 to June 12,2015 the bull market and June 19,2015 to February 19,2016 the bear market,top 60 circulation market value in SME market as the research data and calculated the correlation coefficient between the stock. Then we used minimum spanning tree and community network method to address the data and built the community structure of the stock. Afterwards based on the community structure,we chose our star stocks who connected more neighbors in the community. Furthermore we used K-means clustering method to select categories of members in less stock. These stocks we called edge class stock,and we also analyzed the particularity of them. Finally we will compare the similarities and differences of the bull and bear market and get our results.