A Novel Time-Aware Food Recommender System based on Deep Learning and Graph Clustering

In the era of personalized recommendation systems, there exists a burgeoning need for algorithms capable of adapting to users’ preferences dynamically. Food recommendation systems face unique challenges due to the temporal nature of mealtime preferences and seasonal variations. This paper introduces a novel TimeAware Food Recommender System that integrates deep learning techniques (to capture individual preferences) with graph clustering methodologies to provide personalized and temporally relevant food suggestions. By amalgamating these approaches, the Time-Aware Food Recommender System offers recommendations that align with users’ tastes, mealtime preferences, and seasonal variations. Evaluation using real-world datasets demonstrates the superiority of the Time-Aware Food Recommender System over traditional recommendation methods, showcasing its potential for enhancing user satisfaction in food recommendation platforms.