Title |
Cutting-Edge Time-Sensitive Food Recommender System Utilizing Deep Learning and Graph Clustering |
Abstract |
There is a consensus that food recommender systems can positively influence dietary habits, guiding users towards healthier choices. This project aims to innovate upon existing meal suggestion methods by disregarding conventional criteria such as nutritional value, community preferences, time constraints, and specialty foods. The proposed system comprises two main components: automated meal ideas based on content and user-generated dinner recommendations. Initially, graph clustering categorizes food items and consumers into groups, followed by the application of machine learning techniques. Furthermore, a meticulous approach evaluates temporal and community-specific factors to enhance the quality of meal plans delivered to users. Analysis of "Allrecipes.com" data confirmed the effectiveness of the suggested cooking recommendation methodology |
Keywords |
Ingredients in food, temporal considerations, new users and items, and community elements |
Reserch Area |
Engineering |
Reserch Paper |
AIJFR2403005 - V2 I3 - 29-36 - Australia.pdf |
Author(s) |
Michael Lyon, Dr. Steffy Fleming |
Country |
Australia |