Enhancing Personalized Travel Recommendations: Integrating User Behavior and Content Analysis

In the research presented in this paper, we focus on overcoming the obstacles of delivering personalized travel recommendations in the tourism sector. It introduces a three-part contribution: initially, it delves into the distinctive challenges of making recommendations in tourism and presents a framework to improve the ranking of trip options in tour operators' search engines. We also propose an innovative method that utilizes the behaviors of tourists and the descriptive content of travel offers to compile a dataset rich in insights about the travel industry. Furthermore, we prove that enhancing listwise learning-to-rank algorithms with an attention mechanism for selecting features significantly boosts the effectiveness of the model beyond traditional probabilistic ranking methods. The research concludes by assessing these ranking models and shedding light on the intricacies of recommending travel offers in the tourism industry.