A quantitative model for intraday stock price changes based on order flows
- 203 Downloads
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.
KeywordsIntra-day price changes market microstructure order flow queuing theory
Unable to display preview. Download preview PDF.
- Hasbrouck J and Sofianos G, The traders of market makers: An empirical analysis of NYSE specialist, Journal of Finance, 48: 1565–1594.Google Scholar
- Cohen K, Conroy R, and Maier S, Market Making and the Changing Structure of the Securities Industry, Rowman and Littlefield, Lanham, 1985.Google Scholar
- Farmer J, Patelli P, and Zovko I, The predictive power of zero intelligence in financial markets, Technical Report, Santa Fe Institute Working Paper, 2003.Google Scholar
- Endo M, Zuo S, and Kishimoto K, Modelling intra-day stock price changes in terms of a continuous double auction system, Transactions of the Japan Society for Industrial and Applied Mathematics, 2006, 16: 305–316.Google Scholar
- Suzuki T, Queueing, A Library of Basal Mathematics (in Japanese), Shokabo, Tokyo, 1972.Google Scholar