Food recommendation towards personalized wellbeing

Abstract

Background

The intersection of nutrition and technology gave birth to the research of food recommendation system (FRS), which marked the transformation of traditional diet to a more personalized and healthy direction. The FRS uses advanced data analysis and machine learning technology to provide customized dietary advice according to users' personal preferences, and nutritional needs, which plays a vital role in promoting public health and reducing disease risks.

Scope and approach

This review presents the architecture of FRS and deeply discusses various recommendation algorithms, including the content-based method, collaborative filtering method, knowledge graph-based method, and hybrid methods. The review further introduces existing data resources and evaluation metrics, and highlights key technologies in user profiling and food analysis. In addition, the wide application of personalized FRS is summarized, and the importance of these systems in satisfying users' dietary preferences and maintaining balanced nutrition is emphasized. Finally, the key challenges and development trends of FRS are deeply analyzed from data level, model level and user experience level.

Key findings and conclusions

Personalized FRS shows great potential in helping users make healthier dietary decisions. Although there are still many challenges, such as dealing with heterogeneous data and interpretability. But with the progress of technology, there will be broader development in the future. For example, the powerful data processing ability of deep learning will effectively improve the accuracy of the system. In addition, the application of interactive recommendation system and large language model will also provide strong support for satisfying user experience and improving acceptance.