Research On The Choice Of Portfolio Investment Under Network Model

In this paper, we study the optimal selection of stock market and its investment effi-ciency by using the network clustering and ranking method. First, by selecting a stock as the network node, the correlation coefficient is used as the connection weights of the nodes, and the social network of the corresponding securities is established. Secondly, the use of louvain clustering algorithm for each quarter of the stock classification, so as to ensure that the same class of stock returns between the synchronization of changes in different types of stock returns are not synchronized. Then, the support vector machine method is used to sort the stocks of each class. Finally, the empirical analysis shows that:under the support of clustering and sorting theory, the securities selection method can improve the investment efficiency and reduce the investment risk.