Importance analysis of travel attributes using a rough set‐based neural network : The case of Iranian tourism industry

Purpose – The purpose of this paper is to contribute to the tourism management literature by: first, developing a hybrid neural network that will be able to predict tourists' overall satisfaction of their travel experience; and second, prioritizing the travel attributes based on their proportional impact on tourists' overall satisfaction of their travel experience in Iran. Design/methodology/approach – A total of 1,870 questionnaires were distributed amongst foreign tourists in the departure lounge of “Imam Khomeini International Airport” over a period of three months. The data were used to develop a hybrid neural network in which the “rough set” is used to reduce travel attributes and the neural network to predict tourists' overall satisfaction of travel experience. After the model proved its predictive accuracy, using the sensitivity analysis of the neural network travel attributes were prioritized based on their impact on tourists' overall satisfaction. Findings – The results were quite promising in that the proposed hybrid neural network was able to predict tourists' overall satisfaction with a relatively low amount of error (RMSE=0.05246). Furthermore, it was demonstrated that rough sets theory is capable to be applied effectively to feature selection of large datasets in the tourism context. Finally, it was found that “improving tourism infrastructures of the country” in addition to “globally promoting the image of Iran” (as a secure and pleasant destination) are of the highest priority for Iran's tourism industry to reach to its full potential. Originality/value – Besides developing a data mining tool which is an efficient means for predicting tourists' overall satisfaction, the paper's findings provide precious information for tourism policy makers in Iran by prioritizing those travel attributes that have the greatest impact on foreign tourists' overall satisfaction of their travel experience.