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

Abstract

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 analysis shows that binarization preserves market correlation structure. Properties of distributions of external fields and couplings as well as industry sector clustering structure are studied for different historical dates and moving window sizes. We found that a heavy positive tail in the distribution of couplings is responsible for the sparse market clustering structure. We also show that discrepancies between the model parameters might be used as a precursor of financial instabilities.

15 pages, 17 figures, 1 table

References in corpus (8)

• Nonequilibrium phase transition in the coevolution of networks and opinions
• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• The Ising Model for Neural Data: Model Quality and Approximate Methods for Extracting Functional Connectivity
• Small-correlation expansions for the inverse Ising problem
• Mean Field Theory For Non-Equilibrium Network Reconstruction
• Sector analysis for a FTSE portfolio of stocks
• Mean-field theory for the inverse Ising problem at low temperatures
• Phase transitions in social networks

Cited by in corpus (7)

• Inverse statistical problems: from the inverse Ising problem to data science
• Using persistent homology to reveal hidden information in neural data
• The appropriateness of ignorance in the inverse kinetic Ising model
• Resummed mean-field inference for strongly coupled data
• Role of Intensive and Extensive Variables in a Soup of Firms in Economy to Address Long Run Prices and Aggregate Data
• A Density Consistency approach to the inverse Ising problem
• Inverse Ising inference from high-temperature re-weighting of observations