Modeling item-item similarities for personalized recommendations on Yahoo! front page

DOI10.1214/11-AOAS475zbMATH Open1231.62207arXiv1111.0416OpenAlexW3103968308MaRDI QIDQ652346FDOQ652346

Authors: Deepak Agarwal, L. Zhang, Rahul Mazumder 

Publication date: 14 December 2011

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

Abstract: We consider the problem of algorithmically recommending items to users on a Yahoo! front page module. Our approach is based on a novel multilevel hierarchical model that we refer to as a User Profile Model with Graphical Lasso (UPG). The UPG provides a personalized recommendation to users by simultaneously incorporating both user covariates and historical user interactions with items in a model based way. In fact, we build a per-item regression model based on a rich set of user covariates and estimate individual user affinity to items by introducing a latent random vector for each user. The vector random effects are assumed to be drawn from a prior with a precision matrix that measures residual partial associations among items. To ensure better estimates of a precision matrix in high-dimensions, the matrix elements are constrained through a Lasso penalty. Our model is fitted through a penalized-quasi likelihood procedure coupled with a scalable EM algorithm. We employ several computational strategies like multi-threading, conjugate gradients and heavily exploit problem structure to scale our computations in the E-step. For the M-step we take recourse to a scalable variant of the Graphical Lasso algorithm for covariance selection. Through extensive experiments on a new data set obtained from Yahoo! front page and a benchmark data set from a movie recommender application, we show that our UPG model significantly improves performance compared to several state-of-the-art methods in the literature, especially those based on a bilinear random effects model (BIRE). In particular, we show that the gains of UPG are significant compared to BIRE when the number of users is large and the number of items to select from is small. For large item sets and relatively small user sets the results of UPG and BIRE are comparable. The UPG leads to faster model building and produces outputs which are interpretable.

Full work available at URL: https://arxiv.org/abs/1111.0416

Recommendations

• Smooth neighborhood recommender systems
• Collaborative filtering for massive multinomial data
• An accurate and scalable collaborative recommender
• scientific article; zbMATH DE number 1756678
• Accelerated learning of user profiles

zbMATH Keywords

matrix factorizationcollaborative filteringrecommender systemsgraphical lassoitem-item similarities

Mathematics Subject Classification ID

Multivariate analysis (62H99) Applications of statistics (62P99) Marketing, advertising (90B60) Communication networks in operations research (90B18)

Cites Work

• LIBLINEAR: a library for large linear classification
• Mixed-Effects Models in S and S-PLUS
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• High-dimensional graphs and variable selection with the Lasso
• Approximate Inference in Generalized Linear Mixed Models
• Sparse inverse covariance estimation with the graphical lasso
• Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data
• Title not available (Why is that?)
• Optimal scaling for various Metropolis-Hastings algorithms.
• Methods of conjugate gradients for solving linear systems
• Trust region Newton method for logistic regression
• Asymptotically efficient adaptive allocation rules
• Title not available (Why is that?)
• Finite-time analysis of the multiarmed bandit problem
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Construction of high-order deceptive functions using low-order Walsh coefficients
• Randomized allocation with nonparametric estimation for a multi-armed bandit problem with covariates
• One-armed bandit problems with covariates
• Arbitrary side observations in bandit problems
• Title not available (Why is that?)

Cited In (8)

• Collaborative filtering for massive multinomial data
• Flexible low-rank statistical modeling with missing data and side information
• Collective matrix completion
• Bayesian hierarchical rule modeling for predicting medical conditions
• Graph link prediction in computer networks using Poisson matrix factorisation
• Smooth neighborhood recommender systems
• Two-level monotonic multistage recommender systems
• Main effects and interactions in mixed and incomplete data frames

Uses Software

• S-PLUS
• LIBLINEAR
• glasso
• ElemStatLearn
• MEMSS

This page was built for publication: Modeling item-item similarities for personalized recommendations on Yahoo! front page

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q652346)