amazon,

Leveraging semantics for recommendation at scale

Follow Mar 26, 2025 · 1 min read
Leveraging semantics for recommendation at scale
Share this

In this talk, we present some of our recent work conducted at Amazon International Machine Learning Australia. First, we present a simple approach to address cold-start recommendation by leveraging semantic information (ACM Recsys ’24). We then introduce a notion of generalization gap in collaborative filtering, and derive a geometric upper bound and a way to meaningfully utilize the geometry of the product metadata to improve recommendations (AISTATS ’25).  We finally present an application of sequential recommendation for complementary product selection (ACM WSDM ’25).

Speaker Bio

Dr Julien Monteil is leading the Machine Learning group at Amazon International Machine Learning Australia, which primarily focuses on the Research and Development of recommender systems for Amazon customers globally. He is also an Adjunct Senior Lecturer at the University of Queensland, School of Civil Engineering. He has 12 years of post-PhD experience in the Research and Development of ML systems for customer-facing applications in retail, automotive, networking, healthcare. He developed and launched dozens of ML systems for Amazon, AWS, IBM, including many systems benefiting millions of customers monthly, and generating dozens of millions yearly in business impact. He authored 50+ peer-reviewed papers and 20+ patents in diverse research communities, including optimization and control, transportation, while now actively contributing to the Machine Learning and Recommender Systems communities.

More Details

  • When: Wed. 26 Mar 2025, at 11am.-12pm (Brisbane time)
  • Speaker: Dr Julien Monteil, Amazon International Machine Learning (Australia)
  • Host: Dr Rocky Chen
  • Venue: 14-217
  • Zoom: https://uqz.zoom.us/j/87431037194
Join Newsletter
Get the latest news right in your inbox. We never spam!