Rethinking Recommendations in Zen and Implementing an Item-to-Item Scheme
summary
Describes how Yandex Zen reworked its recommendation system and implemented an item-to-item recommendation scheme to improve personalized feeds of articles, videos and posts. Covers the platform's challenges with multi-format content from hundreds of thousands of authors and the technical approach used to build and deploy item-to-item recommendations within the existing infrastructure.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 2:33Key Zen metrics
- 6:13Old scheme problems
- 10:05Feed relevance analysis
- 13:24Item-to-Item recommendations
- 19:49Building similarity lists
- 23:30Implementation results
- 25:40Q&A
related talks
41mRecommender Systems: Crafting Effective Personalised Experiences
19mContent Recommendation Within Reach!
37mA primer on recommendation systems.
41mVK Media Recommendations: How We Build the Personalized "For You" Feed
29mThe Challenges of Building a Personalized Recommendation System in E-Commerce
58mRecommender Systems – A Walkthrough
32mLet's talk about Recommendation Systems!
19mX1 Recommendations Platform: Started from the bottom..