On November 6, in the Moscow office of Odnoklassniki, approx. Tech Data Talk # 3 was held, this time the event was dedicated to recommendation systems. Together with colleagues from OK.ru, Joom and SkolTech, we talked about the past RecSys19, as well as about the theory, practice and trends of recommender systems.
Come under the cat if you are interested in recommendation systems.
Inside the post: video recordings of reports and discussions, as well as speaker presentations.
Reports
To be or not to be RecSys 2019 - Vladislav Grozin, Joom
Many people want to go to some kind of conference dedicated to big data analysis or even better recommendation systems, however, this is a serious investment of both time and effort, and company funds, of course, if you are not rich enough to pay for everything yourself :)
But how is it worth it? You will find the answers in the report.
Presentation
HybridSVD pros and cons - Evgeny Frolov, SkolTech
This talk will be about the recently introduced HybridSVD model for building hybrid recommendation systems. You will learn about the key features of the model and its main advantages, as well as understand its differences from the existing matrix factorization methods.
Presentation
How we make group recommendations in OK - Andrey Kuznetsov, OK.ru
A story about how machine learning in OK improves the recommendations of groups, and how such solutions fit into the infrastructure of a large highly loaded project with tens of millions of users.
Presentation
Discussion on the present and future of recommender systems
In order not to miss the next Data Explain, subscribe to our page on timepad