Deep learning feature selection to unhide demographic recommender systems factors

Bobadilla Sancho, Jesus and Gonzalez Prieto, Jose Angel and Ortega Requena, Fernando and Lara Cabrera, Raul (2020). Deep learning feature selection to unhide demographic recommender systems factors. "Neural Computing & Applications", v. 33 ; pp. 7291-7308. ISSN 0941-0643. https://doi.org/10.1007/s00521-020-05494-2.

Description

Title: Deep learning feature selection to unhide demographic recommender systems factors
Author/s:
  • Bobadilla Sancho, Jesus
  • Gonzalez Prieto, Jose Angel
  • Ortega Requena, Fernando
  • Lara Cabrera, Raul
Item Type: Article
Título de Revista/Publicación: Neural Computing & Applications
Date: 23 November 2020
ISSN: 0941-0643
Volume: 33
Subjects:
Freetext Keywords: Feature selection; Collaborative filtering; Demographic information; Matrix factorization; Gradient-basedlocalization; Deep learning
Faculty: E.T.S.I. de Sistemas Informáticos (UPM)
Department: Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (18MB) | Preview

Abstract

Extracting demographic features from hidden factors is an innovative concept that provides multiple and relevant applications. The matrix factorization model generates factors which do not incorporate semantic knowledge. Extracting the existing nonlinear relations between hidden factors and demographic information is a challenging task that can not be adequately addressed by means of statistical methods or using simple machine learning algorithms. This paper provides a deep learning-based method: DeepUnHide, able to extract demographic information from the users and items factors in collaborative filtering recommender systems. The core of the proposed method is the gradient-based localization used in the image processing literature to highlight the representative areas of each classification class. Validation experiments make use of two public datasets and current baselines. The results show the superiority of DeepUnHide to make feature selection and demographic classification, compared to the state-of-art of feature selection methods. Relevant and direct applications include recommendations explanation, fairness in collaborative filtering and recommendation to groups of users.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainPID2019-106493RB-I00DL-CEMGUnspecifiedAumento de la calidad y de la equidad, a grupos minoritarios, en las recomendaciones obtenidas mediante filtrado colaborativo basado en técnicas de Deep Learning

More information

Item ID: 66481
DC Identifier: https://oa.upm.es/66481/
OAI Identifier: oai:oa.upm.es:66481
DOI: 10.1007/s00521-020-05494-2
Official URL: https://link.springer.com/article/10.1007/s00521-020-05494-2
Deposited by: Memoria Investigacion
Deposited on: 31 Jan 2022 16:28
Last Modified: 31 Jan 2022 16:28
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM