Modelling high-frequency limit order book dynamics with support vector machines. (English) Zbl 1406.91511
Summary: We propose a machine learning framework to capture the dynamics of high-frequency limit order books in financial equity markets and automate real-time prediction of metrics such as mid-price movement and price spread crossing. By characterizing each entry in a limit order book with a vector of attributes such as price and volume at different levels, the proposed framework builds a learning model for each metric with the help of multi-class support vector machines. Experiments with real data establish that features selected by the proposed framework are effective for short-term price movement forecasts.
MSC:
| 91G99 | Actuarial science and mathematical finance |
| 68T05 | Learning and adaptive systems in artificial intelligence |
| 93E10 | Estimation and detection in stochastic control theory |
| 93E14 | Data smoothing in stochastic control theory |
| 60G35 | Signal detection and filtering (aspects of stochastic processes) |
| 60H07 | Stochastic calculus of variations and the Malliavin calculus |
Keywords:
high-frequency limit order book; multi-class classifiers; support vector machines (SVMs); machine learningReferences:
| [1] | Biais, B., Martimort, D. and Rochet, J.C., Competing mechanisms in a common value environment. Ecnonmetrica, 2000, 68, 799-837. · Zbl 1055.91538 |
| [2] | Blazejewski, A. and Coggins, R., Application of self-organizing maps to clustering of high-frequency financial data. In Proceedings of the Australasian Workshop on Data Mining and Web Intelligence (DMWI2004), edited by M. Purvis, Vol. 32, pp. 85-90, 2004 (ACS: Dunedin). |
| [3] | Blazejewski, A. and Coggins, R., A local non-parametric model for trade sign inference. Physica A, 2005, 348, 481-495. |
| [4] | Bouchaud, J.P., Mezard, M. and Potters, M., Statistical properties of stock order books: Empirical results and models. Quant. Finance, 2002, 2, 251-256. · Zbl 1408.62172 |
| [5] | Bovier, A., Cerny, J. and Hryniv, O., The opinion game: Stock price evolution from microscopic market modeling. Int. J. Theor. Appl. Finance, 2006, 9, 91-111. · Zbl 1131.91021 |
| [6] | Burges, C.J., A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Disc., 1998, 2, 121-167. |
| [7] | Cartea, Á., Jaimungal, S. and Ricci, J., Buy low, sell high: A high frequency trading perspective. SIAM. J. Financ. Math., 2014, 5(1), 415-444. · Zbl 1308.91199 |
| [8] | Cont, R., Statistical modeling of high-frequency financial data. Signal Proc. Mag. IEEE2011, 28, 16-25. |
| [9] | Cont, R. and de Larrard, A., Order book dynamics in liquid markets: Limit theorems and diffusion approximations, February 2012. Available online at: http://ssrn.com/abstract=1757861. · Zbl 1288.91092 |
| [10] | Cont, R., Stoikov, S. and Talreja, R., A stochastic model for order book dynamics. Oper. Res., 2010, 58, 549-563. · Zbl 1232.91719 |
| [11] | Cortes, C. and Vapnik, V., Support-vector networks. Machine Learn., 1995, 20, 273-297. · Zbl 0831.68098 |
| [12] | Cover, T.M. and Thomas, J.A., Elements of Information Theory, 2nd ed., 2006 (John Wiley & Sons: Hoboken, NJ). · Zbl 1140.94001 |
| [13] | Crammer, K. and Singer, Y., On the algorithmic implementation of multiclass kernel-based vector machines. J. Machine Learn. Res., 2001, 2, 265-292. · Zbl 1037.68110 |
| [14] | Fletcher, T. and Shaww-Taylor, J., Multiple kernel learning with fisher kernels for high frequency currency prediction. Comput. Econ., 2013, 42, 217-240. |
| [15] | Föllmer, H., On entropy and information gain in random fields. Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete, 1973, 26, 207-217. · Zbl 0258.60029 |
| [16] | Foucault, T., Order flow composition and trading costs in a dynamic limit order market. J. Financ. Markets, 1999, 2, 99-134. |
| [17] | Foucault, T., Kadan, O. and Kandel, E., Limit order book as a market for liquidity. Rev. Financ. Stud., 2005, 18, 1171-1217. |
| [18] | Hasbrouck, J., Empirical Market Microstructure: The Institutions, Economics, and Econometrics of Securities Trading, 2006 (Oxford University Press: New York). |
| [19] | Hastie, T. and Tibshirani, R., Classification by pairwise coupling. Ann. Stat., 1998, 26, 451-471. · Zbl 0932.62071 |
| [20] | He, H. and Kercheval, A.N., A generalized birth-death stochastic model for high-frequency order book dynamics. Quant. Finance, 2012, 12, 547-557. · Zbl 1278.91099 |
| [21] | Joachims, T., Making Large-scale Support Vector Machine Learning Practical, 1999 (MIT Press: Cambridge, MA). |
| [22] | Jondeau, E., Perilla, A. and Rockinger, G., Optimal Liquidation Strategies in Illiquid Markets, Vol. 553, 2005 (Springer: Berlin Heidelberg). |
| [23] | Knerr, S., Personnaz, L. and Dreyfus, G., Single-layer learning revisited: A stepwise procedure for building and training a neural network. Neurocomputing, 1990, 68, 41-50. |
| [24] | Linnainmaa, J.T. and Rosu, I., Weather and time series determinants of liquidity in a limit order market. AFA 2009 San Francisco Meetings Paper, October 2009. Available online at: http://ssrn.com/abstract=1108862. |
| [25] | Lo, A.W., MacKinlay, A.C. and Zhang, J., Econometric models of limit-order executions. Working Paper 6257, National Bureau of Economic Research, 1997. |
| [26] | Mercer, J., Functions of positive and negative type and their connection with the theory of integral equations. Philos. Trans. Royal Soc. London, 1909, 209, 415-446. · JFM 40.0408.02 |
| [27] | Nadeau, C. and Bengio, Y., Inference of the generalization Error. Machine Learn., 2003, 52, 239-291. · Zbl 1039.68104 |
| [28] | Ng, A., CS229 lecture notes, part V: Support vector machines. Technical report, Stanford University, 2012. |
| [29] | Parlour, C., Price dynamics in limit order markets. Rev. Financ. Stud., 1998, 11, 789-816. |
| [30] | Parlour, C. and Seppi, D.J., Limit Order Market: A Survey, 2008 (Elsevier: North-Holland). |
| [31] | Platt, J.C., Fast training of support vector machines using sequential minimal optimization. In Advances in Kernel Methods, edited by B. Schölkopf, C.J.C Burges and A.J. Smola, Vol. 3, 185-208, 1999 (MIT Press: Cambridge, MA). |
| [32] | Popper, N., Times topic: High-frequency trading. Technical report. The New York Times, 2012. |
| [33] | Rosu, I., A dynamic model of the limit order book. Rev. Financ. Stud., 2009, 22, 4601-4641. |
| [34] | Shabolt, J. and Taylor, J., Neural Networks and the Financial Markets: Predicting, Combining and Portfolio Optimisation, 2002 (Springer: London). · Zbl 1022.91031 |
| [35] | Shek, H.H.S., Modeling high frequency market order dynamics using self-excited point process, September 2011. Available online at: http://ssrn.com/abstract=1668160. |
| [36] | Tino, P., Nikolaev, N. and Yao, X., Volatility forecasting with sparse Bayesian kernel models. In Proceedings of the 8th Joint Conference on Information Sciences 2005, Vol. 3, Salt Lake City, UT, 21-26 July 2005, pp. 1189-1192. |
| [37] | Zheng, B., Moulines, E. and Abergel, F., Price jump prediction in a limit order book. J. Math. Finance, 2013, 3, 242-255. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
