Randomness as the Security Levels of Investments

We propose to use the degree of randomness of high frequency price time series for the purpose of measuring the security levels of stock investments. We employ the RMT-test (quantitative version) as a tool to measure the randomness. We use the tick-wise prices of selected stocks in Tokyo Stock Exchange Market for three years from 2007 to 2009. We select 14 industrial sectors that satisfy the conditions for the RMT-test to apply. The condition to choose the 14 sectors is that a selected sector has at least 10 stocks having data length longer than 170,000. From each sector, we choose 4 most active stocks and compare their randomness levels. It is shown that the stock of the highest level of randomness performs better than the stock of the lowest level of randomness in each of the 14 selected sectors, throughout the following year.