RecSys FR meetup 7th edition: Videos and slides available

The 7th edition of the RecSysFR meetup has been held on the 25th of September 2017 at Tinyclues. For those who missed the presentations or would like to see them again, please find below the links to the slides and videos recorded during the meetup.

Artem Kozhevnikov, Tinyclues, Predictive quality metrics @ tinyclues

Enno Shioji, former Adform, now Zalando, Use of feature embeddings in advertisement
Slides: (to come)

Elena Smirnova, Lowik Chanussot, Amine Benhalloum, Criteo, Highlights on most interesting RecSys papers

https://www.youtube.com/watch?v=1EJc1SvCXyE

Next meetup should be held in December. If you wish to host it or be a speaker, do not hesitate to volunteer!

September 25th meetup: Registrations opened

Save the date.

We’ll have another RecsysFR session on September 25th at 19:00.

The meetup will be hosted by TinyClues.

We’ll start with an introduction word by TinyClues. We’ll then continue with three talks:

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.

Reco team – 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.

The talks will be followed by a casual networking time over food and drinks.

Regsiter here: https://www.meetup.com/RecSysFR/events/243267759

RecSys FR meetup 6th edition: Videos and slides available

The 6th edition of the RecSysFR meetup has been held on the 27th of June 2017 at Criteo. For those who missed the presentations or would like to see them again, please find below the links to the slides and videos recorded during 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
Slides: http://ogrisel.github.io/decks/2017_dotai_neural_recsys/#1

Robbert Van Der Pluijm, Bibblio Labs, How we built a ‘local popularity’ recommender

Next meetup should be held in September. If you wish to host it or be a speaker, do not hesitate to volunteer. Do not forget the RecSys conference in Como, Italy at the end of August! Also, if you are not afraid to cross the channel for more RecSys, here is the link to the Recsys London meetups organized by Robbert Van Der Pluijm: https://www.meetup.com/RecSys-London/

June 27th meetup: Registration is opened

Save the date.

We’ll have another RecsysFR session on June 27th at 19:00.

The meetup will be hosted by Criteo.

We’ll start with an introduction word by Criteo.

We’ll then continue with three talks:

• 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”

The talks will be followed by a casual networking time over food and drinks.

Please register here on meetup.com

February 1st meetup: the slides.

The slides of the 5th RecsysFR meetup are now available online.

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

February 1st Meetup: Registrations are open

We’ll have another RecsysFR session on February 1st at 19:00 in Meetic office.

The meetup is free, you only have to register on: https://www.meetup.com/fr-FR/RecSysFR/events/237066566/

We’ll start with an introduction word by Wilfried Logerais from Meetic.

We’ll then continue with three talks:

• Claire Vernade, Télécom ParisTech: “Sequential Learning in the Position-Based Model”

• Thomas Belhalfaoui & Lucas Charrier, Pulpix: “Video recommendation at scale”

• Thomas Nedelec, Criteo: “Content2Vec: a Joint Architecture to use Product Images and Text for the task of Product Recommendation”

The talks will be followed by a casual networking time over food and drinks.

October 6th meetup: the videos

The videos from the 4th RecysFR talks are online:

Slides: http://www.slideshare.net/recsysfr/recsysfr-criteo-presentation

Slides: http://www.slideshare.net/recsysfr/dictionary-learning-for-massive-matrix-factorization

Slides: http://www.slideshare.net/recsysfr/metaprod2vec-simple-product-embeddings-with-sideinformation

Slides: http://www.slideshare.net/recsysfr/what-can-bring-library-metadata-to-the-web-trust-links-and-love

October 6th meetup: the slides.

The slides of the 4th RecsysFR meetup are now available online

Criteo presentation by Etienne Sanson

Dictionary Learning for Massive Matrix Factorization by Arthur Mensch, Inria Parietal

October 6th meetup: registrations are open

We will have a new RecsysFR meetup on October 6th at 19:00. It will take place in Criteo office: 32 rue Blanche, 75009 Paris.

The meetup is free, you only have to register on: http://www.meetup.com/fr-FR/RecSysFR/events/233735523/

After an introduction speech by Etienne Sanson, Senior R&D Engineering Manager at Criteo, we will have three talks:

–  Arthur Mensch, Inria Parietal. “Online Dictionary Learning for Massive Matrix factorization.”

– Flavian Vasile, Criteo. “Meta-Prod2Vec: Simple Product Embeddings with Side-Information.”

– Raphaëlle Lapôtre, BnF. “What kind of value can library metadata bring to the web ? Trust, links and love.”

The talks will be followed by a casual networking time over food and drinks.