基于影响力计算模型的股票网络社团划分方法

Stock Network Community Detection Method Based on Influence Calculating Model

利用复杂系统的能量特性,引入影响力概念,研究动态复杂网络的社团划分方法,以有效地发现股票网络的社团结构.利用股票收盘价,通过引入影响力和结点中心性定义,构建以影响力为权值的股票网络,并提出一种基于影响力计算模型的股票网络中心结点层次聚类算法(based on the center node hierarchical clustering algorithm about the influence calculation model of stock network,BCNHC).BCNHC算法首先引入结点活跃性和影响力的定义,并给出网络中结点的影响力计算模型;然后,基于所引入的结点中心性的度量准则,选取结点中心性大的结点为中心结点,并利用结点间的亲密性和影响力模型确定相邻结点之间影响力关联度;进而,通过优先选择度值最小的结点向中心结点聚集,以降低因相邻结点所属社团不确定而导致的错误聚类;在此基础上,利用社团平均影响力关联度对相邻社团进行聚类,保证社团内所有结点的影响力关联度最大化,直至整个网络模块度最大.最后,在构建的股票网络上的实验比较和分析,验证BCNHC算法的可行性.

Taking advantage of the energy characteristics of complex system, a concept of influence is introduced to research community detection method, so that community structure could be discovered effectively. With regard to the stock closing price, by introducing the definition of influence and node centrality, a stock network is construted with influence which is regarded as the edge weight. This paper proposes an algorithm named stock network hierarchical clustering based on the influence calculating model, which is referred to as BCNHC algorithm. Firstly, BCNHC algorithm introduces the definition of nodes＇ activity and influence, and puts forward the influence calculating model of node in networks in addition. Then, on the basis of measure criterion of the node centrality, the nodes with large node centrality value as the center nodes are selected, and the nodes＇ Intimacy and influence model are utilized to ensure the influence of association between neighbor nodes. Furthermore, the node with minimum degree is gathering toward to center nodes, so as to reduce the error clustering caused by the uncertainty of which community neighbor nodes belong to. On the basis, the neighbor communities are clustered with the average influence of association of communities. It guarantees that influence of association reach to maximization for all the nodes in the community, until the entire networks＇ modularity come to maximum. At last, comparison and analysis of experimental on stock network prove the feasibility of BCNHC algorithm.