Investigating competition in financial markets: a sparse autologistic model for dynamic network data

ABSTRACT

We develop a sparse autologistic model for investigating the impact of diversification and disintermediation strategies in the evolution of financial trading networks. In order to induce sparsity in the model estimates and address substantive questions about the underlying processes the model includes an $L^1$ regularization penalty. This makes implementation feasible for complex dynamic networks in which the number of parameters is considerably greater than the number of observations over time. We use the model to characterize trader behavior in the NYMEX natural gas futures market, where we find that disintermediation and not diversification or momentum tend to drive market microstructure.

KEYWORDS:

• Financial trading networks
• autologistic models
• Lasso penalty
• dynamic networks
• link prediction

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research was partially supported by NSF/DMS award number [1441433].