A Machine Learning Approach to Tourists' Willingness to Revisit Hotels

Machine learning algorithms have been successfully applied to many topics. In the tourism sector, however, their application is very limited. The aim of this study is to apply machine learning algorithms to predict the factors affecting the willingness of domestic and foreign tourists to revisit hotels and to contribute to the hospitality literature. The data were collected from 4 and 5 star hotels in Istanbul by questionnaire method. Convenience sampling method was used to form the sample. Analyses were carried out on a total of 589 data obtained from two groups of tourists, international and domestic. Five different machine learning algorithms, namely Logistic Regression, LSVM, Neural Network, CHAID, and Tree - AS were used to determine the factors affecting tourists' willingness to revisit hotels. As a result of the analysis, it was determined that the Logistic regression algorithm model was the best algorithm with an accuracy rate of 87.609% in determining the factors affecting the desire of tourists to visit hotels again. The most important variable affecting the willingness of domestic and foreign tourists to revisit hotels again was found to be the sharing variable.