Probabilistic factor models for web site recommendation

By Hao Ma, Chao Liu, Irwin King, Michael R. Lyu. 2011

77 citations recorded by the source corpus.

Subfields: Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Signal Processing

Citations in the corpus

SHOPPER: A Probabilistic Model of Consumer Choice with Substitutes and Complements (2017, methodology): “Matrix factorization decomposes observed data of customer/item interactions into latent preferences and item attributes (Canny, 2004; Hu, Koren and Volinsky, 2008; Ma et al., 2011; Wang and Blei, 2011; Gopalan, Hofman and Blei, 2015), potentially with an infinite number of latent parameters (Görür, ”
Learning geographical preferences for point-of-interest recommendation (2013, methodology): “In contrast, recommender systems can also be developed based on implicit user feedback [11], such as the search and click on a web site [17, 5], and the check-in behaviors in LBSNs as we discussed in this paper.”
Fused Matrix Factorization with Geographical and Social Influence in Location-Based Social Networks (2012, methodology): “PMF with Social Regularization (PMFSR) : this method is proposed to include the social friendship under the PMF framework (Ma et al. 2011b) : this is the fused matrix factorization framework with the Multi-center Gaussian Model (FMFMGM).”
Scalable Recommendation with Poisson Factorization (2013, methodology): “The Probabilistic Factor Model (PFM) [23] improves upon GaP by placing a Gamma prior on the item weights as well, and using multiplicative update rules to infer an approximate maximum a posteriori estimate of the latent factors.”
GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation (2014, background): “It tries to optimizes the following objective function [15], min D where D ( A k B ) = i,j A i,j log P B i,j − A i,j + B i,j is the divergence from matrix A to B [20] and Γ( x | α, β ) is a Gamma distribution, parametrized by a share parameter α and a rate parameter β .”
Scalable Recommendation with Hierarchical Poisson Factorization (2015, methodology): “The Probabilistic Factor Model (PFM) [26] improves upon GaP by placing a Gamma prior on the item weights as well, and using multiplicative update rules to infer an approximate maximum a posteriori estimate of the latent factors.”