Optimizing Multi-Criteria Recommender Systems for the Travel and Tourism Sector: A Hybrid Approach Using ANFIS and Particle Swarm Optimization

The rapid expansion of the internet has revolutionized knowledge sharing and decision-making processes, leading to the emergence of recommender systems that help users navigate vast amounts of information online. These systems are particularly valuable in the travel and tourism sector, where users face challenges in selecting suitable hotels, routes, and experiences based on complex factors like personal preferences and budget constraints. This research presents a multi-criteria recommender system designed specifically for the travel industry, leveraging a combination of filtering methods applied to TripAdvisor data. The system enhances recommendation accuracy by considering user preferences, service quality, and the experiences of similar users. To optimize performance further, the study integrates clustering algorithm with the Adaptive Neuro-Fuzzy Inference System (ANFIS) to model complex data relationships. Additionally, Particle Swarm Optimization (PSO) is employed to enhance ANFIS parameters, leading to improved accuracy and prediction outcomes. The results demonstrate significant enhancements in predictive performance, the ANFIS + PSO approach demonstrates superior accuracy and stability, making it highly recommended for future applications that require reliable predictive performance. This research highlights the importance of optimization techniques like PSO in enhancing the capabilities of adaptive and intelligent modeling systems.