Machine Learning Driven Personalization in the Travel Industry: Enhancing Traveller Experiences and Engagement

The integration of machine learning (ML) in the travel industry has revolutionized the way businesses personalize travel experiences, promoting higher levels of satisfaction and participation. This evaluation examines the evolution of ML-based personalization between 2015 and 2024, underscored by key applications, techniques, and implications in different areas, including recommendation systems, dynamic pricing techniques, loyalty schemes, and destination services. While there is ample research evidence demonstrating the efficacy of ML in personalizing travel services based on individual tastes, there is a research gap in the ethical implications of data secrecy, algorithmic bias, and transparency in personalization systems. The ability to balance personalization and ethical data handling is critical to maintaining consumer trust and ensuring fairness in recommendations. Furthermore, while there has been extensive research aimed at improving the experience of the traveller by exploiting data-driven techniques, little has been done to address the real-time fine-tuning of personalized services, particularly in the context of variability in the behavior of travellers during a journey. Another drawback is the minimal exploration of the potential of combining emerging technologies like augmented reality (AR), virtual reality (VR), and the Internet of Things (IoT) with ML to create interactive travel experiences. Future research endeavors should focus on overcoming these constraints by developing more transparent, ethical, and adaptable personalization models while, at the same time, investigating how emerging technologies can further improve the experience of the traveller. This review provides a comprehensive overview of ML applications to travel personalization and outlines lines of future research to overcome the existing constraints and ensure equitable and sustainable practices within the travel business.