Journal ArticleDOI
Matrix Factorization Techniques for Recommender Systems
Reads0
Chats0
TLDR
As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levels.Abstract:
As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levelsread more
Citations
More filters
Book ChapterDOI
Recommender Systems in Industry: A Netflix Case Study
Xavier Amatriain,Justin Basilico +1 more
TL;DR: This chapter uses Netflix personalization as a case study to describe several approaches and techniques used in a real-world recommendation system and pinpoint what it sees as some promising current research avenues and unsolved problems that deserve attention in this domain from an industry perspective.
Journal ArticleDOI
Scalable Content-Aware Collaborative Filtering for Location Recommendation
TL;DR: A scalable Implicit-feedback-based Content-aware Collaborative Filtering (ICCF) framework to incorporate semantic content and to steer clear of negative sampling is proposed, and an efficient optimization algorithm is developed that outperforms several competing baselines.
Journal ArticleDOI
Recommender systems for smart cities
TL;DR: A taxonomy of smart city features, dimensions, actions and goals, and, according to these variables, the existing literature on recommender systems is surveyed, to show current opportunities and challenges where personalized recommendations could be exploited as solutions for citizens, firms and public administrations.
Proceedings ArticleDOI
Relation-Aware Graph Convolutional Networks for Agent-Initiated Social E-Commerce Recommendation
TL;DR: RecoGCN is able to learn meaningful node embeddings in HIN, and consistently outperforms baseline methods in recommendation tasks, and develops a co-attentive mechanism to dynamically assign importance weights to different meta-paths by attending the three-way interactions among users, selling agents and items.
Posted Content
Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence
TL;DR: A novel autoencoder-based model to learn the complex user-POI relations, namely SAE-NAD, which consists of a self-attentive encoder (SAE) and a neighbor-aware decoder (NAD), which adaptively differentiates the user preference degrees in multiple aspects, by adopting a multi-dimensional attention mechanism.
References
More filters
Journal ArticleDOI
Using collaborative filtering to weave an information tapestry
TL;DR: Tapestry is intended to handle any incoming stream of electronic documents and serves both as a mail filter and repository; its components are the indexer, document store, annotation store, filterer, little box, remailer, appraiser and reader/browser.
Proceedings Article
Probabilistic Matrix Factorization
Andriy Mnih,Ruslan Salakhutdinov +1 more
TL;DR: The Probabilistic Matrix Factorization (PMF) model is presented, which scales linearly with the number of observations and performs well on the large, sparse, and very imbalanced Netflix dataset and is extended to include an adaptive prior on the model parameters.
Proceedings ArticleDOI
Factorization meets the neighborhood: a multifaceted collaborative filtering model
TL;DR: The factor and neighborhood models can now be smoothly merged, thereby building a more accurate combined model and a new evaluation metric is suggested, which highlights the differences among methods, based on their performance at a top-K recommendation task.
Proceedings ArticleDOI
Collaborative Filtering for Implicit Feedback Datasets
TL;DR: This work identifies unique properties of implicit feedback datasets and proposes treating the data as indication of positive and negative preference associated with vastly varying confidence levels, which leads to a factor model which is especially tailored for implicit feedback recommenders.
The Netflix Prize
James Bennett,Stan Lanning +1 more
TL;DR: Netflix released a dataset containing 100 million anonymous movie ratings and challenged the data mining, machine learning and computer science communities to develop systems that could beat the accuracy of its recommendation system, Cinematch.