A quantitative model for intraday stock price changes based on order flows

Autor: Meng Li, Kazuo Kishimoto, Xiaofeng Hui, Misao Endo
Rok vydání: 2014
Předmět:
Zdroj: Journal of Systems Science and Complexity. 27:208-224
ISSN: 1559-7067
1009-6124
DOI: 10.1007/s11424-014-3300-9
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: