OVERVIEW OF NETWORK-BASED METHODS FOR ANALYZING FINANCIAL MARKETS

Abstract

Network based methods are suitable for the analysis of large number of financial time series and the better understanding of their interdependencies. Known approaches to reveal the underlying information about the complex structure of these interdependencies include network-wise and vertex-wise measures of the topology, as well as filtering techniques relying on minimum spanning trees, planar graphs, or spectral analysis. The aim of this study is to review relevant graph theoretical and statistical models and techniques for generating and examining the properties of financial networks, obtained by computing time series correlations or causality relationships. In particular, this study reviews literature discussing the time evolution of the observed phenomena from a network perspective, as well as applications in economy and finance, ranging from risk and diversification, through policy making and better understanding crisis impact, to forecasting. The information synthesized in this paper can be useful to gain further insights into this relatively new research area.