Personalized Restaurant Recommendations: A Hybrid Filtering Approach for Mobile Applications

Marvelio, Christopher Matthew
Waworuntu, Alexander

International Journal of New Media Technology
Vol 12 No 1 (2025): Vol 12 No 1 (2025): IJNMT (International Journal of New Media Technology)

Selecting a restaurant that suits your taste can be a major challenge for consumers, especially given the vast array of online dining options. Traditional recommendation systems or simple filtering methods often fail to handle this complexity well. To address these limitations, we developed a mobile app-based restaurant recommendation platform that combines content-based filtering and collaborative filtering methods in a hybrid approach. The application was built using Expo, React Native, Express, and Flask technologies. The evaluation was conducted using the End-User Computing Satisfaction (EUCS) framework, and the results showed a very high user satisfaction rate of 93.9%. This result shows that the recommendation system we developed is effective in providing relevant suggestions and is well received by users.