Slideshare uses cookies to improve functionality and performance, and to provide you with relevant advertising. If you continue browsing the site, you agree to the use of cookies on this website. See our User Agreement and Privacy Policy.

Slideshare uses cookies to improve functionality and performance, and to provide you with relevant advertising. If you continue browsing the site, you agree to the use of cookies on this website. See our Privacy Policy and User Agreement for details.

Successfully reported this slideshow.

Like this presentation? Why not share!

- Evan Estola, Lead Machine Learning ... by MLconf 440 views
- Past, Present & Future of Recommend... by Justin Basilico 61712 views
- Factorization Meets the Item Embedd... by Dawen Liang 58707 views
- (Some) pitfalls of distributed lear... by Yves Raimond 60805 views
- Recommending for the World by Justin Basilico 62678 views
- Balancing Discovery and Continuatio... by Mohammad Hossein ... 59606 views

2,628 views

Published on

No Downloads

Total views

2,628

On SlideShare

0

From Embeds

0

Number of Embeds

1,082

Shares

0

Downloads

28

Comments

0

Likes

2

No embeds

No notes for slide

- 1. Emmys, Oscars, and Machine Learning Algorithms @ Netflix Scale November, 2013 Xavier Amatriain Director -‐ Algorithms Engineering -‐ Ne<lix @xamat
- 2. “In a simple Netlfix-style item recommender, we would simply apply some form of matrix factorization (i.e NMF)”
- 3. What we were interested in: § High quality recommendations Proxy question: § Accuracy in predicted rating § Improve by 10% = $1million!
- 4. From the Netflix Prize to today 2006 2013
- 5. Big Data @Netflix § > 40M subscribers § Ratings: ~5M/day Time § Searches: >3M/day Geo-information § Plays: > 50M/day Impressions Device Info § Streamed hours: Metadata Social Ratings o 5B hours in Q3 2013 Member Behavior Demographics
- 6. 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 § …
- 7. Deep-dive into Netflix Algorithms
- 8. Rating Prediction
- 9. 2007 Progress Prize ▪ Top 2 algorithms ▪ SVD - Prize RMSE: 0.8914 ▪ RBM - Prize RMSE: 0.8990 ▪ Linear blend Prize RMSE: 0.88 ▪ Currently in use as part of Netflix’ rating prediction component ▪ Limitations ▪ Designed for 100M ratings, we have 5B ratings ▪ Not adaptable as users add ratings ▪ Performance issues
- 10. SVD - Definition A[n x m] = U[n x r] Λ [ r x r] (V[m x r])T ▪ A: n x m matrix (e.g., n documents, m terms) ▪ U: n x r matrix (n documents, r concepts) ▪ ▪ Λ: r x r diagonal matrix (strength of each ‘concept’) (r: rank of the matrix) V: m x r matrix (m terms, r concepts)
- 11. SVD - Properties ▪ ‘spectral decomposition’ of the matrix: = u1 u2 x λ1 λ2 ▪ ‘documents’, ‘terms’ and ‘concepts’: § U: document-to-concept similarity matrix § V: term-to-concept similarity matrix § Λ: its diagonal elements: ‘strength’ of each concept x v1 v2
- 12. 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
- 13. 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
- 14. What about the final prize ensembles? ▪ Our offline studies showed they were too computationally intensive to scale ▪ Expected improvement not worth the engineering effort ▪ Plus, focus had already shifted to other issues that had more impact than rating prediction...
- 15. Ranking Ranking
- 16. Ranking § Ranking = Scoring + Sorting + Filtering bags of movies for presentation to a user § Factors § Accuracy § Novelty Key algorithm, sorts titles in most contexts § Diversity § Freshness § Goal: Find the best possible ordering of a set of videos for a user within a specific context in real-time § Scalability § § Objective: maximize consumption & “enjoyment” § …
- 17. 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 RaEng 1
- 18. Example: Two features, linear model 2 3 4 5 Popularity Final Ranking Predicted RaEng 1
- 19. Ranking
- 20. Learning to Rank ▪ Ranking is a very important problem in many contexts (search, advertising, recommendations) ▪ Quality of ranking is measured using ranking metrics such as NDCG, MRR, MAP, FPC… ▪ It is hard to optimize machine-learned models directly on these measures ▪ They are not differentiable ▪ We would like to use the same measure for optimizing and for the final evaluation
- 21. Learning to Rank Approaches § ML problem: construct ranking model from training data 1. Pointwise (Ordinal regression, Logistic regression, SVM, GBDT, …) Loss function defined on individual relevance judgment § 2. Pairwise (RankSVM, RankBoost, RankNet, FRank…) § § 3. Loss function defined on pair-wise preferences Goal: minimize number of inversions in ranking Listwise § Indirect Loss Function (RankCosine, ListNet…) § Directly optimize IR measures (NDCG, MRR, FCP…) § Genetic Programming or Simulated Annealing § Use boosting to optimize NDCG (Adarank) § Gradient descent on smoothed version (CLiMF, TFMAP, GAPfm @cikm13) § Iterative Coordinate Ascent (Direct Rank @kdd13)
- 22. Similarity
- 23. Similars
- 24. What is similarity? § Similarity can refer to different dimensions § Similar in metadata/tags § Similar in user play behavior § Similar in user rating behavior § … § You can learn a model for each of them and finally learn an ensemble
- 25. Graph-based similarities 0.8 0.3 0.3 0.4 0.2 0.3 0.7
- 26. Example of graph-based similarity: SimRank ▪ SimRank (Jeh & Widom, 02): “two objects are similar if they are referenced by similar objects.”
- 27. Final similarity ensemble § Come up with a score of play similarity, rating similarity, tag-based similarity… § Combine them using an ensemble § Weights are learned using regression over existing response § The final concept of “similarity” responds to what users vote as similar
- 28. Row Selection
- 29. Row SelecEon Inputs § Visitor data § Video history § Queue adds § RaEngs § Taste preferences § Predicted raEngs § PVR ranking § etc. § Global data § Metadata § Popularity § etc.
- 30. Row SelecEon Core Algorithm SelecEon constraints Candidate data Groupify Score/Select ParEal selecEon Group selecEon
- 31. SelecEon Constraints • Many business rules and heurisEcs – RelaEve posiEon of groups – Presence/absence of groups – Deduping rules – Number of groups of a given type • Determined by past A/B tests • Evolved over Eme from a simple template
- 32. GroupiﬁcaEon • Ranking of Etles according to ranking algo • Filtering • Deduping • Forma^ng Candidate data • SelecEon of evidence • ... First n selected groups Group for posiEon n +1
- 33. Scoring and SelecEon • Features considered – ARO scorer – Greedy algorithm – Quality of items – Framework supports other methods – Diversity of tags – Quality of evidence § Backtracking – Freshness § Approximate integer programming – Recency – ... § etc.
- 34. Search Recommendations
- 35. Search Recommendation CombinaEon of Diﬀerent models Play Aaer Search: TransiEon on Play aaer Query Play Related to Search: Similarity between user’s (query, play) … • • • Read this paper for a description of a similar system at LinkedIn
- 36. Unavailable Title Recommendations
- 37. Gamification Algorithms
- 38. rating gameGame Rating Mood Selection Algorithm 1. Editorially selected moods 2. Sort them according to users consumption 3. Take into account freshness, diversity...
- 39. More data or better models?
- 40. More data or better models? Really? Anand Rajaraman: Former Stanford Prof. & Senior VP at Walmart
- 41. More data or better models? Sometimes, it’s not about more data
- 42. More data or better models? [Banko and Brill, 2001] Norvig: “Google does not have better Algorithms, only more Data” Many features/ low-bias models
- 43. More data or better models? Sometimes, it’s not about more data
- 44. “Data without a sound approach = noise”
- 45. Conclusion
- 46. More data + Smarter models + More accurate metrics + Better system architectures Lots of room for improvement!
- 47. Xavier Amatriain (@xamat) xavier@netflix.com Thanks! We’re hiring!

No public clipboards found for this slide

Be the first to comment