Fuzzy clustering of mixed data

A fuzzy clustering model for data with mixed features is proposed. The clustering model allows different types of variables, or attributes, to be taken into account. This result is achieved by combining the dissimilarity measures for each attribute by means of a weighting scheme, so as to obtain a distance measure for multiple attributes. The weights are objectively computed during the optimization process. The weights reflect the relevance of each attribute type in the clustering results. Two simulation studies and two empirical applications were carried out that show the effectiveness of the proposed clustering algorithm in finding clusters that would be otherwise hidden if a multi–attributes approach were not pursued.