PRINCIPAL COMPONENT ANALYSIS AND CLUSTERING PROJECT ⛬

PCA & CLUSTERING

DIMENSIONALITY REDUCTION AND GROUPING

Tutorial
Autor: Daniel Carrillo

Description:

With a database that contains socio-economic information on the provinces of Spain, the number of variables is reduced according to the Principal Component Analysis (PCA), and relationships are sought, both between variables and between provinces, for the construction of clusters. This type of project allows building key performance indicators (KPIs) using a linear combination of all the variables in a dataset, measuring the similarity between items or individuals, grouping those with similar behavior or performance or with similar characteristics, and calculating the differences between groups, thus becoming a useful tool for segmentation (for example, customers, stores or products) and pattern detection. In this study, an index that jointly assesses the economic development of the provinces is constructed, and a hierarchical analysis of the clusters or conglomerates formed is carried out.

⭳ DOWNLOAD DATA:

Dataset