RecSys at Spotify - Building and Evaluating Large-Scale Recommender Systems

RecSys at Spotify - Building and Evaluating Large-Scale Recommender Systems

MLOps.community via YouTube Direct link

[] Vector database features

12 of 23

12 of 23

[] Vector database features

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

RecSys at Spotify - Building and Evaluating Large-Scale Recommender Systems

Automatically move to the next video in the Classroom when playback concludes

  1. 1 [] Sanket's preferred coffee
  2. 2 [] Takeaways
  3. 3 [] RecSys are RAGs
  4. 4 [] Evaluating RecSys parallel to RAGs
  5. 5 [] Music RecSys Optimization
  6. 6 [] Dealing with cold start problems
  7. 7 [] Quantity of models in the recommender systems
  8. 8 [] Radio models
  9. 9 [] Evaluation system
  10. 10 [] Infrastructure support
  11. 11 [] Transfer learning
  12. 12 [] Vector database features
  13. 13 [] Listening History Balance
  14. 14 [26:35 - ] LatticeFlow Ad
  15. 15 [] The beauty of embeddings
  16. 16 [] Shift to real-time recommendation
  17. 17 [] Vector Database Architecture Options
  18. 18 [] Embeddings drive personalized
  19. 19 [] Feature Stores vs Vector Databases
  20. 20 [] Spotify product integration strategy
  21. 21 [] Staying up to date with new features
  22. 22 [] Speed vs Relevance metrics
  23. 23 [] Wrap up

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.