An Effective Stock Classification Method Via MDS Based on Modified Mutual Information Distance

Abstract

This paper proposes a multidimensional scaling (MDS) method based on modified mutual information distance (M-MDS) to analyze stock market data. To better describe the relativity of financial data, it is worthwhile to point out that the commonly used proximity matrix in MDS is replaced with modified mutual information distance (M-MI-D) matrix. Refer to M-MI-D, a higher dissimilarity leads to a larger distance. In order to demonstrate the stability and accuracy of M-MDS, logistic time series are used in simulation experiments. In addition, a comparison of this new M-MDS method with classical MDS is given using the stock market data. It is noted that the new M-MDS method shows better stability than that of classical MDS method. Moreover, not only the stocks in the same US stock block, but also the stocks in different blocks have been discussed to illustrate the efficiency of M-MDS method.