Change-point Analysis in Financial Networks

TL;DR

This paper applies sequential change point detection to dynamic financial networks of global stock markets, successfully identifying network changes that often precede market crashes, offering potential early warning signals.

Contribution

It introduces a novel application of change point detection in dynamic financial networks to predict critical regimes before crashes occur.

Findings

Network changes often precede market crashes

Method detects changes prior to known crashes

Potential for early warning system in finance

Abstract

A major impact of globalization has been the information flow across the financial markets rendering them vulnerable to financial contagion. Research has focused on network analysis techniques to understand the extent and nature of such information flow. It is now an established fact that a stock market crash in one country can have a serious impact on other markets across the globe. It follows that such crashes or critical regimes will affect the network dynamics of the global financial markets. In this paper, we use sequential change point detection in dynamic networks to detect changes in the network characteristics of thirteen stock markets across the globe. Our method helps us to detect changes in network behavior across all known stock market crashes during the period of study. In most of the cases, we can detect a change in the network characteristics prior to crash. Our work thus opens the possibility of using this technique to create a warning bell for critical regimes in financial markets.