A Highly Efficient Big Data Mining Algorithm Based on Stock Market

Abstract

This article proposes a new algorithm which includes two stages. First, the Pearson correlation coefficient is used to calculate the similarity data, and the activity of stock money flow was calculated by combined the probability generating function (P.G.F.) of stationary waiting time and stationary queue length. Second, the discrete time Geo/G/1 queue with a Bernoulli gated service is proposed in calculating money flow by data mining of stock. The new algorithm could calculate data in real time, and each investor could see the real-time data mining graphics. Investors could establish their quantitative trading strategies based on the new money flow model. The proposed algorithm exploits the nature behind stock data. The experimental results show that the authors' approach can be automatically implemented by the investment strategy and know the future trend of the stock market, as well as the economic development of the region, according to the results of the stock data mining in a certain region.