Towards an efficient tourism recommendation system using multi-objective evolutionary optimization

The Recommendation System (RS) serves as a technology delivering precise suggestions to users. However, focusing only on recommendation accuracy proves insufficient, given the diverse requirements of users. In addressing this limitation, our paper introduces a collaborative filtering recommendation model based on multi-objective optimization. This model concurrently optimizes accuracy, diversity, novelty, and coverage of recommendations. Using a multi-objective evolutionary algorithm, the proposed approach is evaluated using a substantial dataset of tourism destination recommendations in Indonesia. The results highlight its capability not only to enhance accuracy recommendations but also to offer commendable performance in coverage and diversity criteria. Our experimental results demonstrate the increased effectiveness of the recommendation approach over conventional user-based collaborative filtering methods. This highlights its ability to enhance the overall recommendation experience by considering multiple objectives to meet diverse user needs in a comprehensive approach.