VK Media Recommendations: How We Build the Personalized "For You" Feed
summary
Describes how VKontakte built a new personalized “For You” media recommendations feed, focusing on machine learning, analytics, and backend engineering. Covers which ML algorithms are applicable for personalized media recommendation and the end-to-end pipeline for serving those recommendations.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 2:31Personalized feed creation
- 9:14Content ranking models
- 15:26Similar post generation
- 21:32Backend architecture optimization
- 25:52Analytics and A/B testing
- 31:13Summary
- 40:20Q&A
related talks
46mFeed and Recommendation Architecture at VKontakte
03mServing Billions of Personalized News Feeds with AI
41mRecommender Systems: Crafting Effective Personalised Experiences
41mRethinking Recommendations in Zen and Implementing an Item-to-Item Scheme
23mML-Powered Search & Recommendation 101
48mPersonalization in 10 Milliseconds
29mThe Challenges of Building a Personalized Recommendation System in E-Commerce
32mLet's talk about Recommendation Systems!