Tourist market segmentation with linear and non-linear techniques

Abstract The need for in-depth knowledge of tourist market segments and the need to overcome the limitations of using linear techniques to analyse non-linear relationships requires a re-assessment of generally used approaches such as cluster analysis and multiple linear regression. The objectives of the research are (1) to consider the use of self-organising (SOM) neural networks for segmenting tourist markets and (2) to analyse the predictive ability of backpropagation (BP) neural networks for classifying tourists from follow-up surveys by using the output provided by a SOM neural network. The findings of the SOM neural network modelling indicate three natural clusters. In addition, the predictive ability of the BP neural network model appears to be superior to that of MLR static filter and logistic regression models. The BP neural network model developed for this application appears suitable for deployment (i.e. classification of tourists from follow-up surveys).