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

  • Stanislav S. Borysov
  • Yasser Roudi
  • Alexander V. Balatsky
Regular Article


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.


Statistical and Nonlinear Physics 


  1. 1.
    N.F. Johnson, P. Jefferies, P.M. Hui, Financial Market Complexity (Oxford University Press, Oxford, 2003)Google Scholar
  2. 2.
    D. Sornette, Why Stock Markets Crash: Critical Events in Complex Financial Systems (Princeton University Press, Princeton, 2009)Google Scholar
  3. 3.
    R. Albert, A.L. Barabási, Rev. Mod. Phys. 74, 47 (2002)CrossRefADSzbMATHGoogle Scholar
  4. 4.
    K. Kacperski, J.A. Hołyst, Phys. Lett. A 254, 53 (1999)CrossRefADSGoogle Scholar
  5. 5.
    K. Kiyono, Z.R. Struzik, Y. Yamamoto, Phys. Rev. Lett. 96, 068701 (2006)CrossRefADSGoogle Scholar
  6. 6.
    A.L. Barabási, R. Albert, Science 286, 509 (1999)CrossRefADSMathSciNetGoogle Scholar
  7. 7.
    S.N. Dorogovtsev, J.F.F. Mendes, Evolution of Networks: From Biological Nets to the Internet and WWW (Physics) (Oxford University Press, New York, 2003)Google Scholar
  8. 8.
    Handbook of Graphs and Networks: From the Genome to the Internet, edited by S. Bornholdt, H.G. Schuster (John Wiley & Sons, New York, 2003)Google Scholar
  9. 9.
    P. Gai, S. Kapadia, Philos. Trans. R. Soc. London A 466, 2401 (2010)ADSMathSciNetzbMATHGoogle Scholar
  10. 10.
    M. Newman, SIAM Rev. Soc. Ind. Appl. Math. 45, 167 (2003)zbMATHGoogle Scholar
  11. 11.
    P. Fronczak, A. Fronczak, J.A. Hołyst, Eur. Phys. J. B 59, 133 (2007)CrossRefADSzbMATHGoogle Scholar
  12. 12.
    S.H. Strogatz, Nature 410, 268 (2001)CrossRefADSGoogle Scholar
  13. 13.
    P. Holme, M.E.J. Newman, Phys. Rev. E 74, 056108 (2006)CrossRefADSGoogle Scholar
  14. 14.
    K. Klemm, V.M. Eguíluz, R. Toral, M. San Miguel, Phys. Rev. E 67, 026120 (2003)CrossRefADSGoogle Scholar
  15. 15.
    T. Bury, Physica A 392, 1375 (2013)CrossRefADSGoogle Scholar
  16. 16.
    E.T. Jaynes, Phys. Rev. 106, 620 (1957)CrossRefADSMathSciNetzbMATHGoogle Scholar
  17. 17.
    E.T. Jaynes, Phys. Rev. 108, 171 (1957)CrossRefADSMathSciNetGoogle Scholar
  18. 18.
    E. Schneidman, M.J. Berry, R. Segev, W. Bialek, Nature 440, 1007 (2006)CrossRefADSGoogle Scholar
  19. 19.
    Y. Roudi, J. Tyrcha, J. Hertz, Phys. Rev. E 79, 051915 (2009)CrossRefADSGoogle Scholar
  20. 20.
    Y. LeCun, S. Chopra, R. Hadsell, M. Ranzato, F.J. Huang, Energy-Based Models, in Predicting Structured Data (The MIT Press, Cambridge, 2007), pp. 191–246Google Scholar
  21. 21.
    J. Maskawa, Physica A 311, 563 (2002)CrossRefADSMathSciNetzbMATHGoogle Scholar
  22. 22.
    T. Bury, Eur. Phys. J. B 86, 1 (2013)CrossRefMathSciNetGoogle Scholar
  23. 23.
    H.L. Zeng, R. Lemoy, M. Alava, J. Stat. Mech. 2014, P07008 (2014)CrossRefMathSciNetGoogle Scholar
  24. 24.
    P.E. Vértes, R.M. Nicol, S. Chapman, N. Watkins, D.A. Robertson, E.T. Bullmore, Front. Syst. Neurosci. 5, 75 (2011)CrossRefGoogle Scholar
  25. 25.
    C. Hommes, Quant. Financ. 1, 149 (2001)CrossRefMathSciNetGoogle Scholar
  26. 26.
    R. Mantegna, Eur. Phys. J. B 11, 193 (1999)CrossRefADSGoogle Scholar
  27. 27.
    J.P. Onnela, A. Chakraborti, K. Kaski, J. Kertsz, A. Kanto, Phys. Scr. 2003, 48 (2003)CrossRefGoogle Scholar
  28. 28.
    G. Bonanno, G. Caldarelli, F. Lillo, S. Micciché, N. Vandewalle, R. Mantegna, Eur. Phys. J. B 38, 363 (2004)CrossRefADSGoogle Scholar
  29. 29.
    C. Lee, J. Lee, A. Lee, Statistics for Business and Financial Economics, 3rd edn. (Springer, New York, 2013)Google Scholar
  30. 30.
    R.S. Pindyck, D.L. Rubinfeld, in Econometric Models and Economic Forecasts (Irwin/McGraw-Hill, Boston, 1998), Vol. 4Google Scholar
  31. 31.
    A. Utsugi, K. Ino, M. Oshikawa, Phys. Rev. E 70, 026110 (2004)CrossRefADSGoogle Scholar
  32. 32.
    B. Podobnik, D. Wang, D. Horvatic, I. Grosse, H.E. Stanley, Europhys. Lett. 90, 68001 (2010)CrossRefADSGoogle Scholar
  33. 33.
    D.J. Fenn, M.A. Porter, S. Williams, M. McDonald, N.F. Johnson, N.S. Jones, Phys. Rev. E 84, 026109 (2011)CrossRefADSGoogle Scholar
  34. 34.
    S.I. Amari, K. Kurata, H. Nagaoka, IEEE Trans. Neural Netw. 3, 260 (1992)CrossRefGoogle Scholar
  35. 35.
    T. Tanaka, Phys. Rev. E 58, 2302 (1998)CrossRefADSGoogle Scholar
  36. 36.
    V. Sessak, R. Monasson, J. Phys. A 42, 055001 (2009)CrossRefADSMathSciNetGoogle Scholar
  37. 37.
    E. Aurell, M. Ekeberg, Phys. Rev. Lett. 108, 090201 (2012)CrossRefADSGoogle Scholar
  38. 38.
    J. Sohl-Dickstein, P.B. Battaglino, M.R. DeWeese, Phys. Rev. Lett. 107, 220601 (2011)CrossRefADSGoogle Scholar
  39. 39.
    H.C. Nguyen, J. Berg, Phys. Rev. Lett. 109, 050602 (2012)CrossRefADSGoogle Scholar
  40. 40.
    L. Laloux, P. Cizeau, J.P. Bouchaud, M. Potters, Phys. Rev. Lett. 83, 1467 (1999)CrossRefADSGoogle Scholar
  41. 41.
    S.S. Borysov, A.V. Balatsky, PLoS One 9, e105874 (2014)CrossRefADSGoogle Scholar
  42. 42.
    R. Coelho, S. Hutzler, P. Repetowicz, P. Richmond, Physica A 373, 615 (2007)CrossRefADSGoogle Scholar
  43. 43.
    A.A. Hagberg, D.A. Schult, P.J. Swart, in Proceedings of the 7th Python in Science Conference (SciPy2008), Pasadena, CA USA, 2008, pp. 11–15Google Scholar
  44. 44.
    P. Ravikumar, M.J. Wainwright, J.D. Lafferty, Ann. Statist. 38, 1287 (2010)CrossRefMathSciNetzbMATHGoogle Scholar
  45. 45.
    Y. Roudi, J. Hertz, Phys. Rev. Lett. 106, 048702 (2011)CrossRefADSGoogle Scholar

Copyright information

© EDP Sciences, SIF, Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Stanislav S. Borysov
    • 1
    • 2
  • Yasser Roudi
    • 1
    • 3
  • Alexander V. Balatsky
    • 4
    • 1
  1. 1.Nordita, Center for Quantum Materials, KTH Royal Institute of Technology and Stockholm UniversityStockholmSweden
  2. 2.Nanostructure Physics, KTH Royal Institute of TechnologyStockholmSweden
  3. 3.The Kavli Institute for Systems Neuroscience, NTNUTrondheimNorway
  4. 4.Institute for Materials Science, Los Alamos National LaboratoryLos AlamosUSA

Personalised recommendations