A QUANTITATIVE MODEL FOR INTRADAY STOCK PRICE CHANGES BASED ON ORDER FLOWS

• Published in: Journal of systems science and complexity 2014-02, Vol.27 (1), p.208-224
• Main Authors: Li, Meng, Hui, Xiaofeng, Endo, Misao, Kishimoto, Kazuo
• Format: Article
• Language: English
• Subjects: Complex Systems; Control; Mathematics; Mathematics and Statistics; Mathematics of Computing; Operations Research/Decision Theory; Statistics; Systems Theory; 价格变化; 定单; 定量模型; 流量; 股价; 证券交易所; 马尔可夫模型; 马尔可夫过程
• ISSN: 1009-6124; 1559-7067
• DOI: 10.1007/s11424-014-3300-9

This paper proposes a double Markov model of the double continuous auction for describing intra-day price changes. The model splits intra-day price changes as the repetition of one tick price moves and assumes order arrivals are independent Poisson random processes. The dynamic process of price formation is described by a birth-death process of the double M/M/1 server queue corresponding to the best bid/ask. The initial depths of the best bid and ask are defined as different constants depending on the last price change. Thus, the price changes in the model follow a first-order Markov process. As the initial depth of the best bid/ask is originally larger than that of the opposite side when the last price is down/up, the model may explain the negative autocorrelations of the price of the best bid/ask. The estimated parameters are based on the real tick-by-tick data of the Nikkei 225 futures listed in Osaka Stock Exchanges. The authors find the model accurately predicts the returns of Osaka Stock Exchange average.