Consumer behaviour in the tourism context is important in formulating successful marketing strategies and customized services. This study investigates consumer behaviour in tourism using a Decision Tree model based on demographic, behavioural, and preference-based characteristics. The data from 400 survey respondents was used to segment consumers into three groups: Budget- Conscious Travellers (30%), Moderate Travellers (50%), and Luxury-Oriented Travellers (20%). The preprocessing steps included cleansing the data to remove duplicate and illogical instances, as well as feature selection and encoding for model compatibility. The accuracy of the Decision Tree model was 92.5%, while precision, recall, and F1-Score were 91.8%, 90.7%, and 91.2%, respectively. Consumer behaviour depended much on travel budget, income levels, and travel frequency. Hence, these results provided tourism enterprises with practical insights to improve the delivery of services and enhance job satisfaction, thereby increasing optimization in the marketplace. It was also found that factors such as spending, income, and frequency of visits play a significant role in influencing consumer behaviour. Such observations enable tourism businesses to develop targeted marketing strategies and customized services, thereby enhancing customer satisfaction and loyalty. The study also provides a hierarchical decision tree framework, segmenting customers into actionable segments such as “Budget- Conscious Occasional Travellers” and “High-Budget Frequent Travellers”. The current study offers new insights into the hierarchical importance of influencing factors and demonstrates the practical application of machine learning in tourism consumer studies. while the findings should be interpreted in light of limitations related to survey-based data and model sensitivity. The study provides an entry into customized marketing, resource management, and enhanced consumer satisfaction for the tourism industry.
Xiaoxiao Guo (Sun,) studied this question.