Can Latent Features be Interpreted as Users in Matrix Factorization-based Recommender Systems? - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Can Latent Features be Interpreted as Users in Matrix Factorization-based Recommender Systems?

Armelle Brun
Anne Boyer

Abstract

Matrix factorization has proven to be one of the most accurate recommendation approach. However, it faces one main shortcoming: the latent features that result from factoriza- tion, and that represent the underlying relation between users and items, are not directly interpretable. Some works focused on their interpretation, particularly with non-negative matrix factorization. In these works, features are viewed as groups of users, groups of items or as attributes of items, but such interpretations require human expertise. In this paper, we propose to interpret features as users, referred to as representative users. This interpretation relies on the study of the matrices that result from the factorization and on their link with the original rating matrix. Such an interpretation is not only performed automatically, as it does not require any human expertise, but it helps also to explain the recommendations made to users. In addition, we see it as a way to alleviate the new item cold-start problem, without requiring any information about the content of the items. The experiments conducted on several benchmark datasets confirm that the features discovered by a non-negative matrix factorization can be actually interpreted as users and that the representative users (the interpretations of the features), are a reliable source of information that allows to accurately estimate ratings on new items. They are thus a promising way to solve the new item cold-start problem.
No file

Dates and versions

hal-01108807 , version 1 (23-01-2015)

Identifiers

  • HAL Id : hal-01108807 , version 1

Cite

Armelle Brun, Marharyta Aleksandrova, Anne Boyer. Can Latent Features be Interpreted as Users in Matrix Factorization-based Recommender Systems?. WI-IAT IEEE/ACM Web Intelligence Conference, Aug 2014, Varsovie, Poland. ⟨hal-01108807⟩
267 View
0 Download

Share

Gmail Facebook X LinkedIn More