Cargando…

A Ranking Recommendation Algorithm Based on Dynamic User Preference

In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These me...

Descripción completa

Detalles Bibliográficos
Autores principales: Wei, Chunting, Qin, Jiwei, Ren, Qiulin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9698759/
https://www.ncbi.nlm.nih.gov/pubmed/36433279
http://dx.doi.org/10.3390/s22228683
_version_ 1784838899836649472
author Wei, Chunting
Qin, Jiwei
Ren, Qiulin
author_facet Wei, Chunting
Qin, Jiwei
Ren, Qiulin
author_sort Wei, Chunting
collection PubMed
description In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These methods are based on implicit feedback, which can reduce the difficulty of data collection and the time of data preprocessing, but will lead to the lack of entity interaction depth information due to the lack of user satisfaction. This is equivalent to artificially reducing the entity interaction features, limiting the overall performance of the model. To address this problem, we propose a two-stage recommendation model named A-DNR, short for Attention-based Deep Neural Ranking. In the first stage, user short-term preferences are modeled through an attention mechanism network. Then the user short-term preferences and user long-term preferences are fused into dynamic user preferences. In the second stage, the high-order and low-order feature interactions are modeled by a matrix factorization (MF) model and a multi-layer perceptron (MLP) model, respectively. Then, the features are fused through a fully connected layer, and the vectors are mapped to scores. Finally, a ranking list is output through the scores. Experiments on three real-world datasets (Movielens100K, Movielens1M and Yahoo Movies) show that our proposed model achieves significant improvements compared to existing methods.
format Online
Article
Text
id pubmed-9698759
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96987592022-11-26 A Ranking Recommendation Algorithm Based on Dynamic User Preference Wei, Chunting Qin, Jiwei Ren, Qiulin Sensors (Basel) Article In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These methods are based on implicit feedback, which can reduce the difficulty of data collection and the time of data preprocessing, but will lead to the lack of entity interaction depth information due to the lack of user satisfaction. This is equivalent to artificially reducing the entity interaction features, limiting the overall performance of the model. To address this problem, we propose a two-stage recommendation model named A-DNR, short for Attention-based Deep Neural Ranking. In the first stage, user short-term preferences are modeled through an attention mechanism network. Then the user short-term preferences and user long-term preferences are fused into dynamic user preferences. In the second stage, the high-order and low-order feature interactions are modeled by a matrix factorization (MF) model and a multi-layer perceptron (MLP) model, respectively. Then, the features are fused through a fully connected layer, and the vectors are mapped to scores. Finally, a ranking list is output through the scores. Experiments on three real-world datasets (Movielens100K, Movielens1M and Yahoo Movies) show that our proposed model achieves significant improvements compared to existing methods. MDPI 2022-11-10 /pmc/articles/PMC9698759/ /pubmed/36433279 http://dx.doi.org/10.3390/s22228683 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wei, Chunting
Qin, Jiwei
Ren, Qiulin
A Ranking Recommendation Algorithm Based on Dynamic User Preference
title A Ranking Recommendation Algorithm Based on Dynamic User Preference
title_full A Ranking Recommendation Algorithm Based on Dynamic User Preference
title_fullStr A Ranking Recommendation Algorithm Based on Dynamic User Preference
title_full_unstemmed A Ranking Recommendation Algorithm Based on Dynamic User Preference
title_short A Ranking Recommendation Algorithm Based on Dynamic User Preference
title_sort ranking recommendation algorithm based on dynamic user preference
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9698759/
https://www.ncbi.nlm.nih.gov/pubmed/36433279
http://dx.doi.org/10.3390/s22228683
work_keys_str_mv AT weichunting arankingrecommendationalgorithmbasedondynamicuserpreference
AT qinjiwei arankingrecommendationalgorithmbasedondynamicuserpreference
AT renqiulin arankingrecommendationalgorithmbasedondynamicuserpreference
AT weichunting rankingrecommendationalgorithmbasedondynamicuserpreference
AT qinjiwei rankingrecommendationalgorithmbasedondynamicuserpreference
AT renqiulin rankingrecommendationalgorithmbasedondynamicuserpreference