The Lifestyles of Families through Fuzzy C-Means Clustering

Abstract

The objective of this report is the analysis of the data arising from the Family Lifestyles survey conducted by the University of Bari “A. Moro” (2012-2013) through the construction of indicators of socio-economic hardship and the identification of family profiles during the current period of crisis. The approach used in this work in order to synthesize and measure the conditions of hardship of a population is based on the so-called “Totally Fuzzy and Relative” method employing a Fuzzy Sets technique in order to obtain a measure of relative incidence in a population from the statistical information provided by a plurality of indicators [1]. The subsequent step involved considering a clustering procedure (Fuzzy c-means) with the objective of outlining various profiles, not defined a priori, to be assigned to each family with different socio-economic behaviours [2]. This clustering method allows, compared to conventional methods, a set of data to belong not only to a main cluster but also to two or more clusters with “fuzzy” profiles.

The contribution is the result of joint reflections by the authors, with the following contributions attributed to S. Montrone (chapters 1), to P. Perchinunno (chapters 3), to Maria Rosaria Zitolo ( 2.1 and 2.2) and to S. L’Abbate (chapters 2.3). The conclusions are the result of the common considerations of the authors. The data used in this paper are the result of a survey funded by the Cassa di Risparmio di Puglia entitled: “Analisi statistica territoriale della povertà urbana attraverso la costruzione di indicatori di disagio socio-economico”.