Fuzzy cluster and validity indices in a socio-economic context
by Silvestro Montrone; Paola Perchinunno; Samuela L'Abbate
International Journal of Business Intelligence and Data Mining (IJBIDM), Vol. 12, No. 2, 2017

Abstract: The multidimensional nature of socio-economic hardship requires a multidimensional research approach, oriented toward advanced solutions, to be able to capture the changing dimensions of the problem at hand. One of such approaches consists of abandoning traditional dichotomous logic in favour of a semantically richer fuzzy classification, in which each unit belongs and, at the same time, does not belong to a given category. Cluster analysis allows us to identify the profiles of families who meet certain descriptive characteristics not defined a priori. The approach used in this work to synthesise and measure hardship conditions is based on a clustering procedure known as fuzzy clustering by local approximation of membership (FLAME), and based on defining the neighbourhood of each object and identifying cluster-supporting objects. This clustering method not only allows for each instance of a dataset to belong to a unique main cluster, but also that each instance can be shared by two or more clusters on the ground of suitably defined 'fuzzy profiles'.

Online publication date: Tue, 23-May-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business Intelligence and Data Mining (IJBIDM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com