Robust Clustering of Banks in Argentina

FERNANDO GARCIA

Revista de Economía y Estadística

Facultad de Ciencias Económicas - Universidad Nacional de Córdoba

Lugar: Cordoba; Año: 2020 vol. 56 p. 21 - 21

0034-8066

he purpose of this paper is to classify and characterize 64 banks, active as of2010 in Argentina, by means of robust techniques used on information gathered during the period 2001-2010. Based on the strategy criteria established in(Wang 2007) and (Werbin 2010), seven variables were selected. In agreementwith bank theory, four ?natural? clusters were obtained, named ?Personal?,?Commercial?, ?Typical? and ?Other banks?. In order to understand thisgrouping, projection pursuit based robust principal component analysis wasconducted on the whole set showing that essentially three variables can beattributed the formation of different clusters. In order to reveal each groupinner structure, we used R package mclust to fit a finite Gaussian mixture tothe data. This revealed approximately a similar component structure, granting a common principal components analysis as in (Boente and Rodrigues,2002). This allowed us to identify three variables which suffice for groupingand characterizing each cl