Evolution of portuguese regional unemployment patterns from 2004 to 2009.

The data mining methodology, in particular the cluster analysis technique, is an important ally in the study of economic patterns in a multivariate framework. Aware of its analytical importance this paper adopts such method of study to identify groups of Portuguese administrative regions that share similar patterns regarding some characteristics of unemployed register individuals. The regional distribution of the unemployed individual characteristics is of core importance for the development of public policies directed to fight the unemployment phenomenon, especially in times of crisis. The research is based on annual cross-section data, from the Portuguese public employment service, for the period of 6 years (from 2004 to 2009). The analysis over time tries to find out if there are persistent regional trends especially when the aggregate unemployment rate rises.

VIVO