Applying Random Matrix Theory Approach for Making Portfolio Enable to Beat the Market

Subject Areas : Financial engineering

N.S. Safavi Mobarhana ¹ ( Department of financial management, Science and Research Branch, Islamic Azad University, Tehran, Iran )
Gholamreza Jafari ² ( Department of Physics, Shahid Beheshti University, Tehran, Iran )
Ali Saeedi ³ ( Department of Accountings, Tehran North Branch, Islamic Azad University, Tehran, Iran )

Received: 2017-06-12 Accepted : 2017-12-03 Published : 2018-03-21

Keywords: correlation matrix, network, Portfolio, random matrix theory, complex systems, market return,

Abstract :

We applied Random Matrix Theory making a portfolio enables to beat the market. On the basis of previous findings, the largest eigenvalue represents the influence of the entire market that is common to all stocks. We analyzed cross-correlation between returns of different stock market indices (S&p500, DJ USA, DAX Germany, FTSE100 England, HSI Hong Kong for efficient markets and TSE Iran, SSE180 China and MXX Mexico for emerging markets) for 730 trading days from May 2012 to October 2014 by using Random Matrix Theory (RMT). Looking at the largest eigenvalue and components (stocks) of the largest eigenvector (demonstrating market mode or trend) and calculating share of every stock in market trend, we could categorize stocks in terms of their impact on the trend in 3 groups: high, middle and low or no impact on market trend. Then we created 3 portfolio in this respect for Tehran stock market. The results shows the portfolio consisting of high impact stocks can beat the market return.