Dynamics of Cluster Structures in Stock Market Networks

A. Kocheturov, M. Batsyn and P. Pardalos
Additional contact information
A. Kocheturov: Center for Applied Optimization, University of Florida, USA
M. Batsyn: NRU HSE, Nizhny Novgorod, Russia
P. Pardalos: NRU HSE, Nizhny Novgorod, Russia

Journal of the New Economic Association, 2015, vol. 28, issue 4, 12-30

Abstract: In recent 15 years network analysis has been actively applied for studying financial markets. In this paper we present a network-based analysis of stock markets of USA and Sweden. We extract and study special cluster structures of networks built from correlation matrices of stock returns for these stock markets. A cluster structure of a network is extracted by solving the p-median problem which chooses p central stocks (medians) and partitions all stocks into p clusters around these medians - centers. The objective function maximizes the sum of correlations between each stock and the median of its cluster. The obtained cluster structure is represented by an undirected disconnected weighted graph, which components are star-graphs with one central vertex (median) and several leaf vertices connected only with the median by weighted edges. Our main observation is that in non-crisis periods cluster structures of stock market networks change more chaotically, while during crises they demonstrate more stable behavior and smaller changes. Thus an increase in stability of the cluster structure for a stock market network obtained by means of the p-median problem solution can serve as an indicator of a coming crisis.

Keywords: dynamics; cluster structure; stock markets; p-median problem; clustering; crisis; network analysis (search for similar items in EconPapers)
JEL-codes: C65 G17 (search for similar items in EconPapers)
Date: 2015
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.econorus.org/repec/journl/2015-28-12-30r.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nea:journl:y:2015:i:28:p:12-30

Access Statistics for this article

Journal of the New Economic Association is currently edited by Victor Polterovich and Aleksandr Rubinshtein

More articles in Journal of the New Economic Association from New Economic Association Contact information at EDIRC.
Bibliographic data for series maintained by Alexey Tcharykov ().