Personalized Recommendation User Experience in Tourism Digital Products: A Case-Based Reasoning Approach

The study examines the delicate balance between personalization and user privacy in tourism digital products, focusing on personalized recommendation systems. While the extensive use of user data to create tailored recommendations enhances user experience, it also raises significant concerns regarding privacy and data security. To address these challenges, this research evaluates the effectiveness of various models—Differential Privacy, Federated Learning, Homomorphic Encryption, Data Minimization, and Case-Based Reasoning (CBR)—in balancing privacy protection and personalization. Among these approaches, CBR emerges as the most effective. By leveraging historical user cases, CBR minimizes the need for extensive data collection, ensuring strong privacy safeguards while enabling adaptive learning and personalized recommendations. Additionally, it promotes transparency, empowering users to understand and control how their data is utilized—a crucial factor in building trust within the tourism sector. A comparative analysis of the five models, using survey data, reveals that CBR outperforms its counterparts in three key areas: data privacy protection, personalization effectiveness, and user transparency. CBR consistently achieves the highest mean scores across these criteria. Statistical analysis further confirms the significance of these differences, with CBR explaining the largest portion of the variability in effectiveness scores. This research underscores CBR’s potential as the optimal model for developing privacy-conscious and user-centric recommendation systems in tourism digital products. Its implementation could drive future innovations in the industry, aligning technological advancements with user trust and satisfaction.