U.S. stock market interaction network as learned by the Boltzmann machine

Borysov, Stanislav S.; Roudi, Yasser; Balatsky, Alexander V.

doi:10.1140/epjb/e2015-60282-3

Title: U.S. stock market interaction network as learned by the Boltzmann machine

Journal Article · Mon Dec 07 00:00:00 EST 2015 · European Physical Journal. B, Condensed Matter and Complex Systems

DOI:https://doi.org/10.1140/epjb/e2015-60282-3· OSTI ID:1258452

Borysov, Stanislav S. ^[1]; Roudi, Yasser ^[2]; Balatsky, Alexander V. ^[3]

KTH Royal Institute of Technology and Stockholm Univ., Stockholm (Sweden)
KTH Royal Institute of Technology and Stockholm Univ., Stockholm (Sweden); The Kavli Institute for Systems Neuroscience (Trondheim)
KTH Royal Institute of Technology and Stockholm Univ., Stockholm (Sweden); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Here, we study historical dynamics of joint equilibrium distribution of stock returns in the U.S. stock market using the Boltzmann distribution model being parametrized by external fields and pairwise couplings. Within Boltzmann learning framework for statistical inference, we analyze historical behavior of the parameters inferred using exact and approximate learning algorithms. Since the model and inference methods require use of binary variables, effect of this mapping of continuous returns to the discrete domain is studied. The presented results show that binarization preserves the correlation structure of the market. Properties of distributions of external fields and couplings as well as the market interaction network and industry sector clustering structure are studied for different historical dates and moving window sizes. We demonstrate that the observed positive heavy tail in distribution of couplings is related to the sparse clustering structure of the market. We also show that discrepancies between the model’s parameters might be used as a precursor of financial instabilities.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC52-06NA25396

OSTI ID:: 1258452

Report Number(s):: LA-UR-15-28956; PII: 1814

Journal Information:: European Physical Journal. B, Condensed Matter and Complex Systems, Vol. 88, Issue 12; ISSN 1434-6028

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 17 works

Citation information provided by
Web of Science

References (58)

Sector analysis for a FTSE portfolio of stocks Coelho, R.; Hutzler, S.; Repetowicz, P. Physica A: Statistical Mechanics and its Applications, Vol. 373 https://doi.org/10.1016/j.physa.2006.02.050	journal	January 2007
Why Stock Markets Crash Sornette, Didier https://doi.org/10.1515/9781400829552	journal	January 2003
Financial markets as nonlinear adaptive evolutionary systems Hommes, C. H. Quantitative Finance, Vol. 1, Issue 1 https://doi.org/10.1080/713665542	journal	January 2001
High-dimensional Ising model selection using ℓ1-regularized logistic regression Ravikumar, Pradeep; Wainwright, Martin J.; Lafferty, John D. The Annals of Statistics, Vol. 38, Issue 3 https://doi.org/10.1214/09-aos691	journal	June 2010
Mean-Field Theory for the Inverse Ising Problem at Low Temperatures Nguyen, H. Chau; Berg, Johannes Physical Review Letters, Vol. 109, Issue 5 https://doi.org/10.1103/physrevlett.109.050602	journal	August 2012
Networks of equities in financial markets Bonanno, G.; Caldarelli, G.; Lillo, F. The European Physical Journal B - Condensed Matter, Vol. 38, Issue 2 https://doi.org/10.1140/epjb/e2004-00129-6	journal	March 2004
Market structure explained by pairwise interactions Bury, Thomas Physica A: Statistical Mechanics and its Applications, Vol. 392, Issue 6 https://doi.org/10.1016/j.physa.2012.10.046	journal	March 2013
Hierarchical structure in financial markets Mantegna, R. N. The European Physical Journal B, Vol. 11, Issue 1 https://doi.org/10.1007/s100510050929	journal	September 1999
Time-lag cross-correlations in collective phenomena Podobnik, B.; Wang, D.; Horvatic, D. EPL (Europhysics Letters), Vol. 90, Issue 6 https://doi.org/10.1209/0295-5075/90/68001	journal	June 2010
Evolution of networks Dorogovtsev, S. N.; Mendes, J. F. F. Advances in Physics, Vol. 51, Issue 4 https://doi.org/10.1080/00018730110112519	journal	June 2002
Small-correlation expansions for the inverse Ising problem Sessak, Vitor; Monasson, Rémi Journal of Physics A: Mathematical and Theoretical, Vol. 42, Issue 5 https://doi.org/10.1088/1751-8113/42/5/055001	journal	January 2009
Exploring complex networks Strogatz, Steven H. Nature, Vol. 410, Issue 6825 https://doi.org/10.1038/35065725	journal	March 2001
Emergence of Scaling in Random Networks Barabási, Albert-László; Albert, Réka Science, Vol. 286, Issue 5439 https://doi.org/10.1126/science.286.5439.509	journal	October 1999
Weak pairwise correlations imply strongly correlated network states in a neural population Schneidman, Elad; Berry, Michael J.; Segev, Ronen Nature, Vol. 440, Issue 7087 https://doi.org/10.1038/nature04701	journal	April 2006
Topological isomorphisms of human brain and financial market networks Vértes, Petra Frontiers in Systems Neuroscience, Vol. 5 https://doi.org/10.3389/fnsys.2011.00075	journal	January 2011
Phase transitions in social networks Fronczak, P.; Fronczak, A.; Hołyst, J. A. The European Physical Journal B, Vol. 59, Issue 1 https://doi.org/10.1140/epjb/e2007-00270-8	journal	September 2007
Financial Market Complexity Johnson, Neil F.; Jefferies, Paul; Hui, Pak Ming https://doi.org/10.1093/acprof:oso/9780198526650.001.0001	book	July 2003
Cross-Correlation Asymmetries and Causal Relationships between Stock and Market Risk Borysov, Stanislav S.; Balatsky, Alexander V. PLoS ONE, Vol. 9, Issue 8 https://doi.org/10.1371/journal.pone.0105874	journal	August 2014
Statistical pairwise interaction model of stock market Bury, Thomas The European Physical Journal B, Vol. 86, Issue 3 https://doi.org/10.1140/epjb/e2013-30598-1	journal	March 2013
Statistics for Business and Financial Economics Lee, Cheng-Few; Lee, John C.; Lee, Alice C. https://doi.org/10.1007/978-1-4614-5897-5	book	January 2013
Information geometry of Boltzmann machines Amari, S.; Kurata, K.; Nagaoka, H. IEEE Transactions on Neural Networks, Vol. 3, Issue 2 https://doi.org/10.1109/72.125867	journal	March 1992
Statistical mechanics of complex networks Albert, Réka; Barabási, Albert-László Reviews of Modern Physics, Vol. 74, Issue 1 https://doi.org/10.1103/RevModPhys.74.47	journal	January 2002
Anomalous oscillations of average transient lifetimes near crises Kacperski, Krzysztof; Ho/klyst, Janusz A. Physics Letters A, Vol. 254, Issue 1-2 https://doi.org/10.1016/S0375-9601(99)00083-3	journal	April 1999
Criticality and Phase Transition in Stock-Price Fluctuations Kiyono, Ken; Struzik, Zbigniew R.; Yamamoto, Yoshiharu Physical Review Letters, Vol. 96, Issue 6 https://doi.org/10.1103/PhysRevLett.96.068701	journal	February 2006
Nonequilibrium phase transition in the coevolution of networks and opinions Holme, Petter; Newman, M. E. J. Physical Review E, Vol. 74, Issue 5 https://doi.org/10.1103/PhysRevE.74.056108	journal	November 2006
Nonequilibrium transitions in complex networks: A model of social interaction Klemm, Konstantin; Eguíluz, Víctor M.; Toral, Raúl Physical Review E, Vol. 67, Issue 2 https://doi.org/10.1103/PhysRevE.67.026120	journal	February 2003
Information Theory and Statistical Mechanics Jaynes, E. T. Physical Review, Vol. 106, Issue 4 https://doi.org/10.1103/PhysRev.106.620	journal	May 1957
Information Theory and Statistical Mechanics. II Jaynes, E. T. Physical Review, Vol. 108, Issue 2 https://doi.org/10.1103/PhysRev.108.171	journal	October 1957
Ising model for neural data: Model quality and approximate methods for extracting functional connectivity Roudi, Yasser; Tyrcha, Joanna; Hertz, John Physical Review E, Vol. 79, Issue 5 https://doi.org/10.1103/PhysRevE.79.051915	journal	May 2009
Ordered phase and non-equilibrium fluctuation in stock market Maskawa, Jun-ichi Physica A: Statistical Mechanics and its Applications, Vol. 311, Issue 3-4 https://doi.org/10.1016/S0378-4371(02)00818-X	journal	August 2002
Financial interaction networks inferred from traded volumes Zeng, Hong-Li; Lemoy, Rémi; Alava, Mikko Journal of Statistical Mechanics: Theory and Experiment, Vol. 2014, Issue 7 https://doi.org/10.1088/1742-5468/2014/07/P07008	journal	July 2014
Asset Trees and Asset Graphs in Financial Markets Onnela, J. -P.; Chakraborti, A.; Kaski, K. Physica Scripta, Vol. T106, Issue 1 https://doi.org/10.1238/Physica.Topical.106a00048	journal	January 2003
Random matrix theory analysis of cross correlations in financial markets Utsugi, Akihiko; Ino, Kazusumi; Oshikawa, Masaki Physical Review E, Vol. 70, Issue 2 https://doi.org/10.1103/PhysRevE.70.026110	journal	August 2004
Temporal evolution of financial-market correlations Fenn, Daniel J.; Porter, Mason A.; Williams, Stacy Physical Review E, Vol. 84, Issue 2 https://doi.org/10.1103/PhysRevE.84.026109	journal	August 2011
Mean-field theory of Boltzmann machine learning Tanaka, Toshiyuki Physical Review E, Vol. 58, Issue 2 https://doi.org/10.1103/PhysRevE.58.2302	journal	August 1998
Inverse Ising Inference Using All the Data Aurell, Erik; Ekeberg, Magnus Physical Review Letters, Vol. 108, Issue 9 https://doi.org/10.1103/PhysRevLett.108.090201	journal	March 2012
New Method for Parameter Estimation in Probabilistic Models: Minimum Probability Flow Sohl-Dickstein, Jascha; Battaglino, Peter B.; DeWeese, Michael R. Physical Review Letters, Vol. 107, Issue 22 https://doi.org/10.1103/PhysRevLett.107.220601	journal	November 2011
Noise Dressing of Financial Correlation Matrices Laloux, Laurent; Cizeau, Pierre; Bouchaud, Jean-Philippe Physical Review Letters, Vol. 83, Issue 7 https://doi.org/10.1103/PhysRevLett.83.1467	journal	August 1999
Mean Field Theory for Nonequilibrium Network Reconstruction Roudi, Yasser; Hertz, John Physical Review Letters, Vol. 106, Issue 4 https://doi.org/10.1103/PhysRevLett.106.048702	journal	January 2011
Why Stock Markets Crash Sornette, Didier; Sornette, Didier https://doi.org/10.23943/princeton/9780691175959.001.0001	journal	March 2017
Statistics for Business and Financial Economics Lee, Cheng F.; Lee, John C.; Lee, Alice C. https://doi.org/10.1142/3803	book	August 1999
Why Stock Markets Crash Sornette, Didier https://doi.org/10.1515/9781400885091	book	April 2017
Small-correlation expansions for the inverse Ising problem Sessak, Vitor; Monasson, Rémi arXiv https://doi.org/10.48550/arxiv.0811.3574	text	January 2008
High-dimensional Ising model selection using ${\ell_1}$-regularized logistic regression Ravikumar, Pradeep; Wainwright, Martin J.; Lafferty, John D. arXiv https://doi.org/10.48550/arxiv.1010.0311	text	January 2010
Temporal Evolution of Financial Market Correlations Fenn, Daniel J.; Porter, Mason A.; Williams, Stacy arXiv https://doi.org/10.48550/arxiv.1011.3225	text	January 2010
Inverse Ising inference using all the data Aurell, Erik; Ekeberg, Magnus arXiv https://doi.org/10.48550/arxiv.1107.3536	text	January 2011
Mean-field theory for the inverse Ising problem at low temperatures Nguyen, H. Chau; Berg, Johannes arXiv https://doi.org/10.48550/arxiv.1204.5375	text	January 2012
Market structure explained by pairwise interactions Bury, Thomas arXiv https://doi.org/10.48550/arxiv.1210.8380	text	January 2012
Cross-correlation asymmetries and causal relationships between stock and market risk Borysov, Stanislav S.; Balatsky, Alexander V. arXiv https://doi.org/10.48550/arxiv.1401.8106	text	January 2014
Anomalous oscillations of average transient lifetimes near crises Kacperski, Krzysztof; Holyst, Janusz A. arXiv https://doi.org/10.48550/arxiv.chao-dyn/9811007	text	January 1998
Ordered phase and non-equilibrium fluctuation in stock market Maskawa, Jun-ichi arXiv https://doi.org/10.48550/arxiv.cond-mat/0110120	text	January 2001
Nonequilibrium transitions in complex networks: a model of social interaction Klemm, Konstantin; Eguiluz, Victor M.; Toral, Raul arXiv https://doi.org/10.48550/arxiv.cond-mat/0210542	text	January 2002
Asset trees and asset graphs in financial markets Onnela, J. -P.; Chakraborti, A.; Kaski, K. arXiv https://doi.org/10.48550/arxiv.cond-mat/0303579	text	January 2003
Hierarchical Structure in Financial Markets Mantegna, Rosario N. arXiv https://doi.org/10.48550/arxiv.cond-mat/9802256	text	January 1998
Noise Dressing of Financial Correlation Matrices Laloux, Laurent; Cizeau, Pierre; Bouchaud, Jean-Philippe arXiv https://doi.org/10.48550/arxiv.cond-mat/9810255	text	January 1998
Sector analysis for a FTSE portfolio of stocks Coelho, R.; Hutzler, S.; Repetowicz, P. arXiv https://doi.org/10.48550/arxiv.physics/0601189	text	January 2006
Phase transitions in social networks Fronczak, Piotr; Fronczak, Agata; Hołyst, Janusz A. arXiv https://doi.org/10.48550/arxiv.physics/0701182	text	January 2007
Weak pairwise correlations imply strongly correlated network states in a neural population Schneidman, Elad; Berry, Michael J.; Segev, Ronen arXiv https://doi.org/10.48550/arxiv.q-bio/0512013	text	January 2005

Cited By (4)

Resummed mean-field inference for strongly coupled data Jacquin, Hugo; Rançon, A. Physical Review E, Vol. 94, Issue 4 https://doi.org/10.1103/physreve.94.042118	journal	October 2016
Inverse statistical problems: from the inverse Ising problem to data science Nguyen, H. Chau; Zecchina, Riccardo; Berg, Johannes Advances in Physics, Vol. 66, Issue 3 https://doi.org/10.1080/00018732.2017.1341604	journal	June 2017
Inverse statistical problems: from the inverse Ising problem to data science Nguyen, H. Chau; Zecchina, Riccardo; Berg, Johannes arXiv https://doi.org/10.48550/arxiv.1702.01522	text	January 2017
Non-criticality of interaction network over system’s crises: A percolation analysis Shirazi, Amir Hossein; Saberi, Abbas Ali; Hosseiny, Ali Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-16223-6	journal	November 2017

Similar Records

Cross-Correlation Asymmetries and Causal Relationships between Stock and Market Risk

Journal Article · Wed Aug 27 00:00:00 EDT 2014 · PLoS ONE · OSTI ID:1258452

Borysov, Stanislav S.; Balatsky, Alexander V.

Thermodynamics of Restricted Boltzmann Machines and Related Learning Dynamics

Journal Article · Sat Sep 15 00:00:00 EDT 2018 · Journal of Statistical Physics · OSTI ID:1258452

Decelle, A.; Fissore, G.

Numerical analysis for finite-range multitype stochastic contact financial market dynamic systems

Journal Article · Wed Apr 15 00:00:00 EDT 2015 · Chaos (Woodbury, N. Y.) · OSTI ID:1258452

Yang, Ge; Wang, Jun; Fang, Wen

Related Subjects

97 MATHEMATICS AND COMPUTING
Boltzman machine
stock correlations
statistical and nonlinear physics

Title: U.S. stock market interaction network as learned by the Boltzmann machine

Citation Formats

References (58)

Cited By (4)

Similar Records

Related Subjects