Coorelation Based Clutering of Stocks Traded in NSE

Abstract

This paper presents a topological classification of top 42 stocks traded in the National Stock Exchange of India based on the co-movements between individual stocks with reference to the financial year 2007 - 2008. The hierarchical structure is obtained using the matrix of correlation coefficients computed between all possible pairs of 42 stocks using hierarchical clustering algorithms. The dynamics of the system is investigated by studying the distribution and time dependence of the correlation coefficients. The empirical results show that it is possible to obtain a meaningful taxonomy based solely on the co-movements between individual stocks and the fundamental distance metric assumption, without any presumptions of the companies' business activity.