Optimized spiral spherical self-organizing map approach to sector analysis – The case of banking

• Optimized spiral spherical self-organizing map is applied to real-life data.
• We investigate the European Union banking sector in the 2000–2011 period.
• We use micro and macro economic data for two separate models.
• Both models reveal the existence of two separate banking clusters.
• Dynamic analysis indicates intensification of integration within the two groups.

The paper presents a comprehensive treatment of the European Union banking sector in the 2000–2011 period. A wide set of economic indicators is used to derive two-level approach: micro and macro topologies. We use the methodology of the optimized spiral spherical self-organizing map, a version of Kohonen’s Self-Organizing Maps, which overcomes some of the major deficiencies found in standard methods. In dynamic analysis we recover the path of the integration process itself by calculating the dynamics of the countries around the sphere and by examining the measure of dispersion. The simultaneous comparison of the micro and macro levels provides deeper insights into the banking sector integration process. Both models, the micro and macro, unveil the formation of two banking clusters, which, with the exception for Greece, coincides with a division between new and old member states. Both clusters intensify integration within their cluster.