Full text

Turn on search term navigation

© 2020. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

Abstract: Collaborative filtering based on matrix factorization has become the reference method for the recommendation of products or services due to the high precision of recommendations it generates. The experimental results carried out on the datasets of MovieLens 100K, MovieLens lM and Netflix demonstrate a clear improvement in terms of quality of predictions and recommendations compared to other matrix factorization techniques. Keywords: Collaborative filtering; matrix factorization; gradient descent; recommendation system. En concreto se han seleccionado los siguientes métodos: * Probabilistic Matrix Factorization (PMF) (Salakhutdinov & Mnih, 2007) * Non-negative Matrix Factorization (NMF) (Lee & Seung,

Details

Title
Optimización del filtrado colaborativo basado en factorización matricial mediante la relevancia de las preferencias de los usuarios
Author
Valdiviezo-Diaz, Priscila 1 ; Ortega, Fernando 2 ; Mayor, Jesús 2 ; Pajuelo-Holguera, Francisco 3 

 Universidad Técnica Particular de Loja, Departamento de Ciencias de la Computación y Electrónica, 110104, Loja, Ecuador 
 Universidad Politécnica de Madrid, ETSI de Sistemas Informáticos, 28031, Madrid, España 
 Universidad de Extremadura, Madrid, España 
Pages
465-478
Publication year
2020
Publication date
Apr 2020
Publisher
Associação Ibérica de Sistemas e Tecnologias de Informacao
ISSN
16469895
Source type
Scholarly Journal
Language of publication
Spanish
ProQuest document ID
2388304715
Copyright
© 2020. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.