Statistical analysis of k-nearest neighbor collaborative recommendation

DOI10.1214/09-AOS759MaRDI QIDQ973879zbMATHFDO

Authors Gérard Biau, Benoît Cadre, Laurent Rouvière

Publication date 26 May 2010

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1010.0499

zbMATH Keywords

consistencyrate of convergencecollaborative recommendationnearest neighbor estimatecosine-type similarity

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Applications of statistics (62P99) Sequential statistical methods (62L99) Communication networks in operations research (90B18)

Abstract: Collaborative recommendation is an information-filtering technique that attempts to present information items that are likely of interest to an Internet user. Traditionally, collaborative systems deal with situations with two types of variables, users and items. In its most common form, the problem is framed as trying to estimate ratings for items that have not yet been consumed by a user. Despite wide-ranging literature, little is known about the statistical properties of recommendation systems. In fact, no clear probabilistic model even exists which would allow us to precisely describe the mathematical forces driving collaborative filtering. To provide an initial contribution to this, we propose to set out a general sequential stochastic model for collaborative recommendation. We offer an in-depth analysis of the so-called cosine-type nearest neighbor collaborative method, which is one of the most widely used algorithms in collaborative filtering, and analyze its asymptotic performance as the number of users grows. We establish consistency of the procedure under mild assumptions on the model. Rates of convergence and examples are also provided.

Recommendations

• Using mixture models for collaborative filtering
• Recommendation systems: A probabilistic analysis
• scientific article; zbMATH DE number 1931838
• Smooth neighborhood recommender systems
• An accurate and scalable collaborative recommender

Cites work

• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• A distribution-free theory of nonparametric regression
• A new approach to collaborative filtering: operator estimation with spectral regularization
• Dependency networks for inference, collaborative filtering, and data visualization
• Exact matrix completion via convex optimization

Cited in

(11)

• scientific article; zbMATH DE number 1931838 (Why is no real title available?)
• Using mixture models for collaborative filtering
• Smooth neighborhood recommender systems
• FST TCS 2003: Foundations of Software Technology and Theoretical Computer Science
• Recommendation systems: A probabilistic analysis
• Why does collaborative filtering work? Transaction-based recommendation model validation and selection by analyzing bipartite random graphs
• Collaborative filtering for massive multinomial data
• Axiomatic analysis of language modelling of recommender systems
• An optimization model for collaborative recommendation using a covariance-based regularizer
• Statistical significance of the Netflix challenge
• Variational Bayesian inference for bipartite mixed-membership stochastic block model with applications to collaborative filtering

This page was built for publication: Statistical analysis of \(k\)-nearest neighbor collaborative recommendation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q973879)