Detecting intraday financial market states using temporal clustering

We propose the application of a high-speed maximum likelihood clustering algorithm to detect temporal financial market states, using correlation matrices estimated from intraday market microstructure features. We first determine the ex-ante intraday temporal cluster configurations to identify market states, and then study the identified temporal state features to extract state signature vectors (SSVs) which enable online state detection. The SSVs serve as low-dimensional state descriptors which can be used in learning algorithms for optimal planning in the high-frequency trading domain. We present a feasible scheme for real-time intraday state detection from streaming market data feeds. This study identifies an interesting hierarchy of system behaviour which motivates the need for timescale-specific state space reduction for participating agents.

[1]  W. Brian Arthur,et al.  Complexity in economic and financial markets: Behind the physical institutions and technologies of the marketplace lie the beliefs and expectations of real human beings , 1995, Complex..

[2]  Cars H. Hommes,et al.  Financial markets as nonlinear adaptive evolutionary systems , 2001 .

[3]  Diane Wilcox,et al.  Hierarchical Causality in Financial Economics , 2014, 1408.5585.

[4]  Dual-listed Companies.  Dual-listed Companies , 2002 .

[5]  Eytan Domany,et al.  Data Clustering Using a Model Granular Magnet , 1997, Neural Computation.

[6]  장훈,et al.  [서평]「Computer Organization and Design, The Hardware/Software Interface」 , 1997 .

[7]  F. Baldovin,et al.  Ensemble Properties of High Frequency Data and Intraday Trading Rules , 2012, 1202.2447.

[8]  Lan Zhang,et al.  A Tale of Two Time Scales , 2003 .

[9]  Asaf Adi,et al.  Complex Event Processing for Financial Services , 2006, 2006 IEEE Services Computing Workshops.

[10]  Ezejiofor Raymond Asika,et al.  Appraisal of Human Resource Accounting on Profitability of Corporate Organization , 2017 .

[11]  Dieter Hendricks,et al.  An unsupervised parallel genetic cluster algorithm for graphics processing units , 2014, ArXiv.

[12]  Joel Hasbrouck,et al.  Measuring the Information Content of Stock Trades , 1991 .

[13]  Noh.  Model for correlations in stock markets , 1999, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  M. Marsili.  Dissecting financial markets: sectors and states , 2002, cond-mat/0207156.

[15]  Eytan Domany,et al.  Clustering data through an analogy to the Potts model , 1995, NIPS.

[16]  Ioane Muni Toke,et al.  Modelling Trades-Through in a Limit Order Book Using Hawkes Processes , 2012 .

[17]  Joel Hasbrouck,et al.  Empirical Market Microstructure: The Institutions, Economics, and Econometrics of Securities Trading , 2007 .

[18]  Jeffrey R. Russell,et al.  Autoregressive Conditional Duration: A New Model for Irregularly Spaced Transaction Data , 1998 .

[19]  Maureen O'Hara,et al.  Market Microstructure Theory , 1995 .

[20]  H. Bauke.  Parameter estimation for power-law distributions by maximum likelihood methods , 2007, 0704.1867.

[21]  Brandon Whitcher,et al.  Asymmetry of information flow between volatilities across time scales , 2009 .

[22]  Mark E. J. Newman,et al.  Power-Law Distributions in Empirical Data , 2007, SIAM Rev..

[23]  E. Bacry,et al.  Hawkes Processes in Finance , 2015, 1502.04592.

[24]  R. Schilling.  Financial Modelling with Jump Processes , 2005 .

[25]  V. Plerou,et al.  A theory of power-law distributions in financial market fluctuations , 2003, Nature.

[26]  M Marsili,et al.  Data clustering and noise undressing of correlation matrices. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  I. Mastromatteo,et al.  On the criticality of inferred models , 2011, 1102.1624.

[28]  L. Glosten,et al.  Market Microstructure: A Survey of Microfoundations, Empirical Results, and Policy Implications , 2005 .

[29]  Jeremy H. Large.  Measuring the resiliency of an electronic limit order book , 2007 .

[30]  M. Dehmer,et al.  Influence of the Time Scale on the Construction of Financial Networks , 2010, PloS one.

[31]  Dariusz Cieslakiewicz,et al.  Unsupervised asset cluster analysis implemented with parallel genetic algorithms on the NVIDIA CUDA platform , 2014 .

[32]  Mathieu Bastian,et al.  Gephi: An Open Source Software for Exploring and Manipulating Networks , 2009, ICWSM.

[33]  The Volume Clock: Insights into the High-Frequency Paradigm , 2012, The Journal of Portfolio Management.

[34]  Muhittin Mungan,et al.  Stability of maximum-likelihood-based clustering methods: exploring the backbone of classifications , 2008, 0809.1398.

[35]  P. Embrechts,et al.  Quantitative Risk Management: Concepts, Techniques, and Tools , 2005 .

[36]  R. Palmer,et al.  Asset Pricing Under Endogenous Expectations in an Artificial Stock Market , 1996 .

[37]  Blatt,et al.  Superparamagnetic clustering of data. , 1998, Physical review letters.

[38]  J. R. Ward,et al.  Fractals and Intrinsic Time - a Challenge to Econometricians , 1999 .

[39]  Geoffrey E. Hinton.  Learning multiple layers of representation , 2007, Trends in Cognitive Sciences.

[40]  Edward M. Reingold,et al.  Graph drawing by force‐directed placement , 1991, Softw. Pract. Exp..

[41]  Aymen Jedidi,et al.  Long-Time Behavior of a Hawkes Process-Based Limit Order Book , 2015, SIAM J. Financial Math..

[42]  Christine M. Anderson-Cook,et al.  Book review: quantitative risk management: concepts, techniques and tools, revised edition, by A.F. McNeil, R. Frey and P. Embrechts. Princeton University Press, 2015, ISBN 978-0-691-16627-8, xix + 700 pp. , 2017, Extremes.

[43]  Clara Vega,et al.  Market Microstructure , 2009, Encyclopedia of Complexity and Systems Science.

[44]  Ananth N. Madhavan,et al.  Market Microstructure: A Survey , 2000 .

[45]  W. Krauth.  Cluster Monte Carlo algorithms , 2003, cond-mat/0311623.

[46]  Lan Zhang,et al.  A Tale of Two Time Scales: Determining Integrated Volatility with Noisy High Frequency Data , 2003 .

[47]  William A. Brock,et al.  PATHWAYS TO RANDOMNESS IN THE ECONOMY: EMERGENT NONLINEARITY AND CHAOS IN ECONOMICS AND FINANCE , 1993 .

[48]  R. N. Mantegna,et al.  Identification of clusters of companies in stock indices via Potts super-paramagnetic transitions , 2000 .

[49]  Aymen Jedidi,et al.  Long Time Behaviour of a Hawkes Process-Based Limit Order Book , 2015 .

[50]  W. Arthur,et al.  Complexity in Economic and Financial Markets , 1995 .

[51]  Emanuel Derman.  The Perception of Time, Risk and Return During Periods of Speculation , 2002 .

[52]  Rose,et al.  Statistical mechanics and phase transitions in clustering. , 1990, Physical review letters.

[53]  Geoffrey J. McLachlan,et al.  Maximum likelihood clustering via normal mixture models , 1996, Signal Process. Image Commun..

[54]  Olivier V. Pictet,et al.  Changing time scale for short‐term forecasting in financial markets , 1996 .

[55]  Joel Hasbrouck,et al.  Trades, quotes, inventories, and information , 1988 .