Recommendation systems have been developed to address the immense volume of information accessible on the Internet. These systems employ filtering methodologies and customize their recommendations by drawing insights from user profiles, ultimately enhancing the relevance and utility of their suggestions. In this paper, we present our system called Smart Food and Restaurant Advisor based on nutritional needs and user profiling (SFRA); a multi-criteria food and restaurant recommendation system designed to prioritize personalized and health-conscious selections. This system uses user profiling to offer customized recommendations that cater to individual preferences, requirements, and geographic locations. Our primary objective is to enhance users’ decision-making processes by promoting healthier and more refined lifestyle choices. The results of the proposed system demonstrate that it is well-suited for promoting a healthier lifestyle while offering comprehensive coverage of users’ practices and preferences.

Recommendation system, user profiling, Machine learning, Multi-criteria methods, Big data analytic, Food and restaurant recommendation, personalized recommendations