Machine Learning & Recommender Systems at Netflix Scale
•
20 gostaram•3,447 visualizações
Video and slides synchronized, mp3 and slide download available at URL http://bit.ly/1fMC8e3. Xavier Amatriain discusses the machine learning algorithms and architecture behind Netflix' recommender systems, offline experiments and online A/B testing. Filmed at qconsf.com. Xavier Amatriain (PhD) is Director of Algorithms Engineering at Netflix. He leads a team of researchers and engineers designing the next wave of machine learning approaches to power the Netflix product. Previous to this, he was a Researcher in Recommender Systems, and neighboring areas such as Data Mining, Machine Learning, Information Retrieval, and Multimedia.
Recomendados
Recomendados
Mais conteúdo relacionado
Mais de C4Media
Mais de C4Media (20)
Último
Último (20)
Machine Learning & Recommender Systems at Netflix Scale
- 1. Machine Learning & Recommender Systems @ Netflix Scale November, 2013 Xavier Amatriain Director - Algorithms Engineering @ Netflix @xamat
- 2. Watch the video with slide synchronization on InfoQ.com! http://www.infoq.com/presentations /machine-learning-netflix InfoQ.com: News & Community Site • 750,000 unique visitors/month • Published in 4 languages (English, Chinese, Japanese and Brazilian Portuguese) • Post content from our QCon conferences • News 15-20 / week • Articles 3-4 / week • Presentations (videos) 12-15 / week • Interviews 2-3 / week • Books 1 / month
- 3. Presented at QCon San Francisco www.qconsf.com Purpose of QCon - to empower software development by facilitating the spread of knowledge and innovation Strategy - practitioner-driven conference designed for YOU: influencers of change and innovation in your teams - speakers and topics driving the evolution and innovation - connecting and catalyzing the influencers and innovators Highlights - attended by more than 12,000 delegates since 2007 - held in 9 cities worldwide
- 4. SVD What we were interested in: ■ High quality recommendations Proxy question: ■ Accuracy in predicted rating ■ Improve by 10% = $1million! Results ● Top 2 algorithms still in production RBM
- 5. From the Netflix Prize to today 2006 2013
- 7. Everything is personalized Ranking Over 75% of what people watch comes from a recommendation
- 9. Support for Recommendations Social Support
- 10. Genre Rows
- 11. Similars
- 12. EVERYTHING is a Recommendation
- 13. Data & Models
- 14. Big Data @Netflix ■ > 40M subscribers ■ Ratings: ~5M/day ■ Searches: >3M/day Time ■ Plays: Geo-information > 50M/day ■ Streamed hours: ○ 5B hours in Q3 2013 Impressions Device Info Metadata Social Ratings Member Behavior Demographics
- 15. Smart Models ■ Regression models (Logistic, Linear, Elastic nets) ■ SVD & other MF models ■ Factorization Machines ■ Restricted Boltzmann Machines ■ Markov Chains & other graph models ■ Clustering (from k-means to HDP) ■ Deep ANN ■ LDA ■ Association Rules ■ GBDT/RF ■ …
- 16. SVD for Rating Prediction ■ User factor vectors ■ Baseline (bias) and item-factors vectors (user & item deviation from average) ■ Predict rating as ■ SVD++ (Koren et. Al) asymmetric variation w. implicit feedback ■ Where ■ are three item factor vectors ■ Users are not parametrized, but rather represented by: ■ R(u): items rated by user u & N(u): items for which the user has given implicit preference (e.g. rated/not rated)
- 17. Restricted Boltzmann Machines ■ Restrict the connectivity in ANN to make learning easier. ■ Only one layer of hidden units. ■ ■ Although multiple layers are possible No connections between hidden units. ■ Hidden units are independent given the visible states.. ■ RBMs can be stacked to form Deep Belief Networks (DBN) – 4th generation of ANNs
- 18. Ranking ■ Ranking = Scoring + Sorting + Filtering bags of movies for presentation to a user ■ Key algorithm, sorts titles in most contexts ■ Goal: Find the best possible ordering of a set of videos for a user within a specific context in real-time ■ Objective: maximize consumption & “enjoyment” ■ Factors ■ ■ ■ ■ ■ ■ Accuracy Novelty Diversity Freshness Scalability …
- 19. Example: Two features, linear model 2 3 4 5 Popularity Linear Model: frank(u,v) = w1 p(v) + w2 r(u,v) + b Final Ranking Predicted Rating 1
- 20. Example: Two features, linear model 2 3 4 5 Popularity Final Ranking Predicted Rating 1
- 21. Ranking
- 23. More data or better models? Really? Anand Rajaraman: Former Stanford Prof. & Senior VP at Walmart
- 24. More data or better models? Sometimes, it’s not about more data
- 25. More data or better models? [Banko and Brill, 2001] Norvig: “Google does not have better Algorithms, only more Data” Many features/ low-bias models
- 26. More data or better models? Sometimes, it’s not about more data
- 27. “Data without a sound approach = noise”
- 30. Cloud Computing at Netflix ▪ Layered services ▪ 100s of services and applications ▪ Clusters: Horizontal scaling ▪ 10,000s of EC2 instances ▪ Auto-scale with demand ▪ Plan for failure ▪ Replication ▪ Fail fast ▪ State is bad ▪ Simian Army: Induce failures to ensure resiliency
- 31. System Overview ▪ Blueprint for multiple personalization algorithm services ▪ Ranking ▪ Row selection ▪ Ratings ▪ … ▪ Recommendation involving multi-layered Machine Learning
- 32. Event & Data Distribution ▪ Collect actions ▪ Plays, browsing, searches, ratings, etc. ▪ Events ▪ Small units ▪ Time sensitive ▪ Data ▪ Dense information ▪ Processed for further use ▪ Saved
- 33. Online Computation ▪ Synchronous computation in response to a member request ▪ Pros: ▪ Good for: ▪ Simple algorithms ▪ Model application ▪ Access to most fresh data ▪ Business logic ▪ Knowledge of full request context ▪ Context-dependence ▪ Compute only what is necessary ▪ Interactivity ▪ Cons: ▪ Strict Service Level Agreements ▪ Must respond quickly … in all cases ▪ Requires high availability ▪ Limited view of data www.netflix.com
- 34. Offline Computation ▪ Asynchronous computation done on a regular schedule ▪ Pros: ▪ Good for: ▪ Batch learning ▪ Model training ▪ Can handle large data ▪ Complex algorithms ▪ Can do bulk processing ▪ Precomputing ▪ Relaxed time constraints ▪ Cons: ▪ Cannot react quickly ▪ Results can become stale
- 35. Nearline Computation ▪ Asynchronous computation in response to a member event ▪ Pros: ▪ Good for: ▪ Incremental learning ▪ User-oriented algorithms ▪ Can keep data fresh ▪ Moderate complexity algorithms ▪ Can run moderate complexity algorithms ▪ Keeping precomputed results fresh ▪ Can average computational cost across users ▪ Change from actions ▪ Cons: ▪ Has some delay ▪ Done in event context
- 36. Where to place components? ▪ Example: Matrix Factorization ▪ Offline: ▪ Collect sample of play data ▪ Run batch learning algorithm to produce factorization ▪ Publish item factors ▪ Nearline: X X≈UVt Aui=b sij=uivj ▪ Solve user factors sij ▪ Compute user-item products ▪ Combine ▪ Online: ▪ Presentation-context filtering ▪ Serve recommendations sij>t V
- 37. Recommendation Results ▪ Precomputed results ▪ Fetch from data store ▪ Post-process in context ▪ Generated on the fly ▪ Collect signals, apply model ▪ Combination ▪ Dynamically choose ▪ Fallbacks
- 38. Conclusion
- 39. More data + Smarter models + More accurate metrics + Better system architectures Lots of room for improvement!
- 41. Watch the video with slide synchronization on InfoQ.com! http://www.infoq.com/presentations/machinelearning-netflix