PERSONALIZED TRAVEL PLANNING WITH DECISION TREE– DRIVEN RECOMMENDATIONS

Abstract

Tourism is one of the fastest-growing industries, with travelers increasingly seeking personalized experiences tailored to their preferences and constraints. Traditional recommendation methods often fail to capture the dynamic requirements of tourists, such as budget, interests, time availability, and location-based factors. This study presents a decision tree–driven recommendation system designed to assist tourists in planning their journeys more effectively. By leveraging decision tree algorithms, the system classifies user preferences and provides optimized travel suggestions, ranging from destinations and attractions to accommodation and activities. The model ensures interpretability, scalability, and adaptability while reducing computational complexity compared to black-box approaches. Experimental evaluations demonstrate that the proposed framework enhances recommendation accuracy, improves user satisfaction, and offers an intelligent alternative to conventional travel planning methods.