Expectation maximization algorithm cluster analysis for UK National Trust visitors

This source preferred by Shuang Cang

Authors: Cang, S.

Journal: Tourism Analysis

Volume: 14

Pages: 637-650

ISSN: 1083-5423

DOI: 10.3727/108354209X12597959359257

This article aims to investigate the segmenting of UK National Trust (NT) visitors based on behavior and motivation for the visit. The main focus of the article is to apply the more powerful, robust, and stable expectation maximization (EM) algorithm cluster analysis method together with PCA (without varimax rotation), which is rarely used in a tourism context, to the NT data set. This study identifies four clusters of NT visitors, and also identifies the most important items (questions) in the classification of NT visitors, which is the satisfaction with the NT service. The intracluster inequality, which means the diversity of the cluster, is also analyzed. Each cluster has its own characteristics and the results of cluster analysis will be useful for future NT marketing management to maximize the benefit to the NT. The diversity of each cluster is also discussed.

This data was imported from Scopus:

Authors: Cang, S.

Journal: Tourism Analysis

Volume: 14

Issue: 5

Pages: 637-650

eISSN: 1943-3999

ISSN: 1083-5423

DOI: 10.3727/108354209X12597959359257

© 2009 Cognizant Comm. Corp. This article aims to investigate the segmenting of UK National Trust (NT) visitors based on behavior and motivation for the visit. The main focus of the article is to apply the more powerful, robust, and stable expectation maximization (EM) algorithm cluster analysis method together with PCA (without varimax rotation), which is rarely used in a tourism context, to the NT data set. This study identifies four clusters of NT visitors, and also identifies the most important items (questions) in the classification of NT visitors, which is the satisfaction with the NT service. The intracluster inequality, which means the diversity of the cluster, is also analyzed. Each cluster has its own characteristics and the results of cluster analysis will be useful for future NT marketing management to maximize the benefit to the NT. The diversity of each cluster is also discussed.

The data on this page was last updated at 04:40 on November 19, 2017.