Advanced Recommender Systems for Ecommerce

Numerous studies have recently proposed and highlighted novel techniques for recommendation, motivating the project of building the next generation of recommender systems for ecommerce platforms. This proposal aims at experimenting with one high-potential technique for modelling the recommendation problem, that makes great usage of the complexity of ecommerce data: Graph Neural Networks (GNNs). GNNs are increasingly used in recommender systems. However, much work remains to develop versatile and robust GNNs for ecommerce data, since the data is large-scale (often millions of users and thousands of items) and heterogeneous (mixed types of data, including images, textual description and categories of items, as well as sociodemographic and behavorial data of users).
The partner will benefit from transfer knowledge in this nascent domain and a strong scientific approach on GNNs for recommendation tasks.

Faculty Supervisor:

Laurent Charlin

Student:

Partner:

Décathlon Canada

Discipline:

Computer science

Sector:

Retail trade

University:

HEC Montréal

Program: