Menu Content/Inhalt
Seminars Print
previous year previous month next month next year
See by year See by month See by week See Today Search Jump to month
Valérie De Bruyckere, Ghent University Print
Thursday, 18 April 2013, 12:15 - 13:15

Valérie De Bruyckere, Ghent University

The Network Structure of the European Financial Sector

Abstract: This paper presents a network based methodology to assess spillovers between financial institutions in Europe. Banks are not only exposed to shocks from common risk factors (macroeconomic risk factors, sovereign risk, financial risk and housing price risk), but also to shocks from all other banks in the system. To do so, this paper relies on Bayesian Model Averaging (BMA) of Locally Weighted Regression models. BMA allows to identify a set of relevant risk factors out of a larger set of potentially important regressors. I illustrate the power of the model in projecting future evolutions in bank equity prices. The model correctly projects the direction of 77% of bank equity price changes over an horizon ranging from one quarter to four quarters ahead. Moreover, I show that the performance of my model increases to 81% due to the use of the Locally Weighted Regression model, further illustrating the usefullness of this model as a stress test tool. Furthermore, I provide insight into the time-varying importance of risk factors, and I analyse the interconnectedness of the financial system both in terms of the strength and probability of the connections. I compute network centrality measures (degree, closeness and betweenness) and show how their relate to different states of the economy.


Location: R42.2.113
Contact: Claude Adan, This e-mail address is being protected from spam bots, you need JavaScript enabled to view it