RecSysFR #7, September 25th 2017

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.