Multi-Domain Recommendation for Restaurants Using GNN Models

The student will develop a recommendation system for restaurants, proposing food selections to customers. This system will be based on GNN models to predict a customer’s need based on both user and order data. The data include previous purchases, data of dishes and similarity of users collected from online food orders. In the first phase the model will be trained on a specific domain (pizza, sushi, etc.) with good and sufficient data. Then the student will apply recent deep learning innovations to cross-domain restaurants with limited data. Through better recommendations for users, the system is expected to increase the value of orders and revenues of restaurant.

Faculty Supervisor:

Ioannis Mitliagkas

Student:

Partner:

UEAT Technologies Inc

Discipline:

Computer science

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

Université de Montréal

Program: