Fuzzy C-Medoids Clustering Of CUB Data to Handle Likert-Type Scales Uncertainty

In investigating customer satisfaction (CS) with products or services the most popular approach still relies on interviews or questionnaire to obtain consumer’s opinions and responses are usually measured by means of Likert-type scales. However, Likert-type data are inherently imprecise and uncertain. Thus, to obtain reliable analysis using such data, an a-posteriori correction must be adopted. Fuzzification procedure is the most common a-posteriori way to deal with uncertainty of Likert-type data, but it requires the subjective definition of the membership function. To overcome this problem, while a cluster analysis is conducted using Likert-type data as segmentation variables, a new approach based on CUB model and Fuzzy C-Medoids Clustering of Mixed Data algorithm (FCMd-CUB) is theoretically and empirically presented in this paper. Advantages of the suggested method are discussed in the conclusion section.