litlas
ログインアカウント作成

The Netflix Recommender System: Algorithms, Business Value, and Innovation

著者: Carlos Alberto Gomez-Uribe, Neil Hunt - ACM Transactions on Management Information Systems 2015 被引用: 1,331

This article discusses the various algorithms that make up the Netflix recommender system, and describes its business purpose. We also describe the role of search and related algorithms, which for us turns into a recommendations problem as well. We explain the motivations behind and review the approach that we use to improve the recommendation algorithms, combining A/B testing focused on improving member retention and medium term engagement, as well as offline experimentation using historical member engagement data. We discuss some of the issues in designing and interpreting A/B tests. Finally, we describe some current areas of focused innovation, which include making our recommender system global and language aware.

Analysis of IncompleteMultivariate DataAnalysis of Incomplete Multivariate DataAnalysis of IncompleteMultivariate DataAnalysis of Incomplete Multivariate DataLatent DirichletAllocationLatent Dirichlet AllocationThe Paradox of Choice:Why More Is LessThe Paradox of Choice: Why More Is LessHierarchical DirichletProcessesHierarchical Dirichlet ProcessesProbabilistic MatrixFactorizationProbabilistic Matrix FactorizationThe Netflix PrizeThe Netflix PrizeFactorization meets theneighborhood: a…Factorization meets the neighborhood: a multifaceted collaborative filtering modelMatrix FactorizationTechniques for…Matrix Factorization Techniques for Recommender SystemsFactorization MachinesFactorization MachinesMachine learning - aprobabilistic…Machine learning - a probabilistic perspectiveLarge-scale validationand analysis of…Large-scale validation and analysis of interleaved search evaluationCaching-awarerecommendations: Nudgin…Caching-aware recommendations: Nudging user preferences towards better caching performanceRelated Pins atPinterest: The Evolutio…Related Pins at Pinterest: The Evolution of a Real-World Recommender SystemDissecting racial biasin an algorithm used to…Dissecting racial bias in an algorithm used to manage the health of populationsAlgorithmic Effects onthe Diversity of…Algorithmic Effects on the Diversity of Consumption on SpotifyArtificial Intelligenceas Augmenting…Artificial Intelligence as Augmenting Automation: Implications for EmploymentCooperative ContentReplacement and…Cooperative Content Replacement and Recommendation in Small Cell NetworksTrends in combating fakenews on social media -…Trends in combating fake news on social media - a surveyModeling uncertainty toimprove personalized…Modeling uncertainty to improve personalized recommendations via Bayesian deep learningHeteGraph: graphlearning in recommender…HeteGraph: graph learning in recommender systems via graph convolutional networksA Survey ofRecommendation Systems…A Survey of Recommendation Systems: Recommendation Models, Techniques, and Application FieldsJoint User-SideRecommendation and…Joint User-Side Recommendation and D2D-Assisted Offloading for Cache-Enabled Cellular Networks With Mobility ConsiderationOptimizing NetworkPerformance Through…Optimizing Network Performance Through Joint Caching and Recommendation Policy for Continuous User Request BehaviorThe Netflix RecommenderSystem: Algorithms…The Netflix Recommender System: Algorithms, Business Value, and Innovation過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。