Google news personalization: scalable online collaborative filtering

@inproceedings{Das2007GoogleNP,
  title={Google news personalization: scalable online collaborative filtering},
  author={Abhinandan Das and Mayur Datar and Ashutosh Garg and Shyamsundar Rajaram},
  booktitle={WWW '07},
  year={2007}
}
Several approaches to collaborative filtering have been studied but seldom have studies been reported for large (several millionusers and items) and dynamic (the underlying item set is continually changing) settings. [] Key Method We generate recommendations using three approaches: collaborative filtering using MinHash clustering, Probabilistic Latent Semantic Indexing (PLSI), and covisitation counts. We combine recommendations from different algorithms using a linear model.

Figures from this paper

HYPNER: A Hybrid Approach for Personalized News Recommendation
TLDR
A personalised news recommendation framework named Hybrid Personalised NEws Recommendation (HYPNER), which combines both collaborative filtering-based and content-based filtering methods and aims at improving the accuracy of news recommendation by resolving the issues of scalability due to large news corpus.
Personalized news recommendation with context trees
TLDR
This paper introduces a class of news recommendation systems based on context trees that can provide high-quality news recommendations to anonymous visitors based on present browsing behaviour and shows that they make accurate and novel recommendations, and that they are sufficiently flexible for the challenges ofNews recommendation.
Online Recommender System Based on Social Network Regularization
TLDR
An online collaborative filtering algorithm which can better use the social information and prior knowledge is proposed and it is proposed that this problem of cold start and users with few ratings is solved.
Time-ordered collaborative filtering for news recommendation
TLDR
A time-ordered collaborative filtering recommendation algorithm (TOCF), which takes the time sequence characteristic of user behaviors into account, and a new method to compute the similarity among different users, named time-dependent similarity, is proposed.
Time-ordered collaborative filtering for news recommendation
TLDR
A time-ordered collaborative filtering recommendation algorithm (TOCF), which takes the time sequence characteristic of user behaviors into account, and a new method to compute the similarity among different users, named time-dependent similarity, is proposed.
Effective hierarchical vector-based news representation for personalized recommendation
TLDR
An effective representation of news and a user model which are used to recommend dynamically changing large number of text documents are proposed, designed with aim to effectively estimate user needs and generate personalized list of items in information space.
The Browsemaps: Collaborative Filtering at LinkedIn
TLDR
This paper presents LinkedIn’s horizontal collaborative filtering infrastructure, known as browsemaps, which enables rapid development, deployment, and computation of collaborative filtering recommendations for almost any use case on LinkedIn.
News recommendation via hypergraph learning: encapsulation of user behavior and news content
TLDR
This paper uses hypergraph to model various high-order relations among different objects in news data, and forms news recommendation as a ranking problem on fine-grained hypergraphs and concludes that the proposed algorithm is capable of effectively handling the so-called cold-start problem.
News Recommendation Model Based on Improved Label Propagation Algorithm
TLDR
A news recommendation model based on community detection is proposed, which builds a friend relationship community by using the users friend relationship and coherent neighborhood propinquity algorithm, and then integrates the collaborative filtering algorithm to recommend news to users.
...
...

References

SHOWING 1-10 OF 31 REFERENCES
GroupLens: an open architecture for collaborative filtering of netnews
TLDR
GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles, and protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction.
Latent semantic models for collaborative filtering
TLDR
A new family of model-based algorithms designed for collaborative filtering rely on a statistical modelling technique that introduces latent class variables in a mixture model setting to discover user communities and prototypical interest profiles.
Item-based collaborative filtering recommendation algorithms
TLDR
This paper analyzes item-based collaborative ltering techniques and suggests that item- based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.
Empirical Analysis of Predictive Algorithms for Collaborative Filtering
TLDR
Several algorithms designed for collaborative filtering or recommender systems are described, including techniques based on correlation coefficients, vector-based similarity calculations, and statistical Bayesian methods, to compare the predictive accuracy of the various methods in a set of representative problem domains.
Application of Dimensionality Reduction in Recommender System - A Case Study
TLDR
This paper presents two different experiments where one technology called Singular Value Decomposition (SVD) is explored to reduce the dimensionality of recommender system databases and suggests that SVD has the potential to meet many of the challenges ofRecommender systems, under certain conditions.
Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main
Latent Dirichlet Allocation
The multiple multiplicative factor model for collaborative filtering
TLDR
Empirical results from the collaborative filtering domain are presented showing that a binary/multinomial MMF model matches the performance of the best existing models while learning an interesting latent space description of the users.
Finding interesting associations without support pruning
  • E. Cohen, Mayur Datar, Cheng Yang
  • Computer Science
    Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073)
  • 2000
TLDR
This work develops a family of algorithms for solving association rule mining, employing a combination of random sampling and hashing techniques and provides an analysis of the algorithms developed and conduct experiments on real and synthetic data to obtain a comparative performance analysis.
An MDP-Based Recommender System
TLDR
The use of an n-gram predictive model is suggested for generating the initial MDP, which induces a Markovchain model of user behavior whose predictive accuracy is greater than that of existing predictive models.
...
...