U.S. stock market interaction network as learned by the Boltzmann machine
- 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.
- 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
Web of Science
Resummed mean-field inference for strongly coupled data
|
journal | October 2016 |
Inverse statistical problems: from the inverse Ising problem to data science
|
journal | June 2017 |
Inverse statistical problems: from the inverse Ising problem to data science | text | January 2017 |
Non-criticality of interaction network over system’s crises: A percolation analysis
|
journal | November 2017 |
Similar Records
Thermodynamics of Restricted Boltzmann Machines and Related Learning Dynamics
Numerical analysis for finite-range multitype stochastic contact financial market dynamic systems