Thanks to Fifty-Five for hosting this meetup! Only two talks for this edition.

Romain WARLOP — Fifty Five
Multi Task DPP for Basket Completion
Determinantal point processes (DPPs) have received significant attention in the recent years as an elegant model for a variety of machine learning tasks, due to their ability to elegantly model set diversity and item quality or popularity. Recent work has shown that DPPs can be effective models for product recommendation and basket completion tasks. We present an enhanced DPP model that is specialized for the task of basket completion, the multi-task DPP. We view the basket completion problem as a multi-class classification problem, and leverage ideas from tensor factorization and multi-class classification to design the multi-task DPP model. We evaluate our model on several real-world datasets, and find that the multi-task DPP provides significantly better predictive quality than a number of state-of-the-art models.
Cristian PEREZ, Stanislas MORBIEU — Kernix
Building a recommender system with Annoy and Word2Vec
The Kernix Lab will talk about the development of a recommender engine at the RecSys MeetUp. We will discuss both strategic and technical considerations for a production ready system. Technically, how we handle cold start, misspelled words and content high renewal rates will be shared.

Thanks to Deezer for hosting this meetup! For privacy reasons, the second talk has not been recorded and slides are not available.

Hugo Dupré, Deezer, Word2Vec and co for music recommendation
Quentin Grossetti, LIP6, An Homophily-based Approach for Fast Post Recommendation in Microblogging Systems

Thanks to TinyClues for hosting the meetup!

Artem Kozhevnikov — Tinyclues
Predictive quality metrics @ tinyclues
Artem Kozhevnikov, lead Data Scientist, will present some quality metrics commonly followed @ tinyclues in order to evaluate the model predictive power. Those metrics are going beyond well known technical metrics like AUC or RMSE and seem to be important in the context of CRM campaigns targeting.
Enno Shioji — Adform
Use of feature embeddings in advertisement
Feature embeddings, especially pre-trained feature embeddings can be a very useful tool in the context of RTB. We will discuss different ways of using them, with emphasis on engineering implications. This will include RNN, Wide & Deep Learning, and a “hacky” way of mimicking the effect of Wide & Deep Learning.
Elena Smirnova, Lowik Chanussot, Amine Benhalloum — Criteo
Highlights on most interesting RecSys papers
RecSys conference was held in Como at the end of August. We will summarize for you the most trendy techniques and results presented at this conference.

Thanks to Criteo for hosting the meetup!

Romain Lerallut, Criteo, Introduction speech
Simon Lefebvre, Antvoice, Injecting semantic links into a graph-based recommender system
Olivier Grisel, Inria, Neural Networks for Recommender Systems
Robbert Van Der Pluijm, Bibblio Labs, How we built a ‘local popularity’ recommender

Thanks to Meetic for hosting this session of the RecSysFR meetup. Because of technical problems, only the first talk is available as a video.

Recommendation @ Meetic by Wilfried Logerais, Meetic

Sequential Learning in the Position-Based Model by Claire Vernade, Télécom ParisTech

Pulpix — Video Recommendation at Scale by Thomas Belhalfaoui & Lucas Charrier, Pulpix

CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task of Product Recommendation by Thomas Nedelec, Criteo

The slides from the talks of the second edition of the RecsysFR meetup are now available online.

Recommendation @ PriceMinister-Rakuten — Road to personalization by Patrick Herrmann
Rakuten Institute of Technology Paris by Laurent Ach
Story of the algorithms behind Deezer Flow by Benoit Mathieu & Thomas Boubca, Deezer
New tools from the bandit literature to improve A/B Testing by Emilie Kaufmann, CNRS & CRIStAL
Tailor-made personalization and recommendation — Sailendra by Régis Lhoste, Sailendra
Recommendations at SensCritique. Mixing social and machine learning by Xavier Rampino, SensCritique

Thanks again to the speakers, to our host: PriceMinister and to the audience. We had a great time and hope to see you at the next event.


Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store