Modeling and application of implicit feedback in personalized recommender systems

Traditional recommendation algorithms usually rely on the user's existing data and historical behavioral records to make recommendations, which often leads to low recommendation accuracy and insufficient personalized experience. To solve these problems, this paper proposes an innovative recomme...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Li, Shuai Wu, Ronghui Wang, Wenbin Hu, Haining Li
Format: Article
Language:English
Published: AIMS Press 2025-03-01
Series:Electronic Research Archive
Subjects:
Online Access:https://www.aimspress.com/article/doi/10.3934/era.2025053
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151278407057408
author Hui Li
Shuai Wu
Ronghui Wang
Wenbin Hu
Haining Li
author_facet Hui Li
Shuai Wu
Ronghui Wang
Wenbin Hu
Haining Li
author_sort Hui Li
collection DOAJ
description Traditional recommendation algorithms usually rely on the user's existing data and historical behavioral records to make recommendations, which often leads to low recommendation accuracy and insufficient personalized experience. To solve these problems, this paper proposes an innovative recommendation algorithm model, neural collaborative filtering with multiple attention mechanism (NCF-MAH). The goal of this model is to enhance the effectiveness of the recommender system. The specific implementation includes constructing a negative sample set and applying matrix decomposition techniques to map user and item IDs to a low-dimensional embedding vector space. In addition, the model processes these embedding vectors using a multi-head attention mechanism to transform them into query vectors, key vectors, and value vectors, and further computes the attention scores and the corresponding weighted sums. Finally, the score prediction is accomplished by fusing the output of the multi-head attention mechanism with the results of the multilayer perceptual machine. The experimental results show that the NCF-MAH model exhibits significant advantages over the baseline model in two key evaluation metrics, hit rate and normalized discount cumulative gain (NDCG), on the MOOC platform and other datasets. Specifically, hit rate and NDCG improved by 13% vs. 9.8% and 15.7% vs. 12.8% when Top-k was set to 10 and 20, respectively.
format Article
id doaj-art-1f7cdce145e043108930eed8ec15f6c9
institution OA Journals
issn 2688-1594
language English
publishDate 2025-03-01
publisher AIMS Press
record_format Article
series Electronic Research Archive
spelling doaj-art-1f7cdce145e043108930eed8ec15f6c92025-08-20T02:26:19ZengAIMS PressElectronic Research Archive2688-15942025-03-013321185120610.3934/era.2025053Modeling and application of implicit feedback in personalized recommender systemsHui Li0Shuai Wu1Ronghui Wang2Wenbin Hu3Haining Li4School of Computer Engineering, Jiangsu Ocean University, Jiangsu 222000, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Jiangsu 222000, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Jiangsu 222000, ChinaSchool of Computer Engineering, Jiangsu Ocean University, Jiangsu 222000, ChinaDepartment of Neurology, General Hospital of Ningxia Medical University, Ningxia 750003, ChinaTraditional recommendation algorithms usually rely on the user's existing data and historical behavioral records to make recommendations, which often leads to low recommendation accuracy and insufficient personalized experience. To solve these problems, this paper proposes an innovative recommendation algorithm model, neural collaborative filtering with multiple attention mechanism (NCF-MAH). The goal of this model is to enhance the effectiveness of the recommender system. The specific implementation includes constructing a negative sample set and applying matrix decomposition techniques to map user and item IDs to a low-dimensional embedding vector space. In addition, the model processes these embedding vectors using a multi-head attention mechanism to transform them into query vectors, key vectors, and value vectors, and further computes the attention scores and the corresponding weighted sums. Finally, the score prediction is accomplished by fusing the output of the multi-head attention mechanism with the results of the multilayer perceptual machine. The experimental results show that the NCF-MAH model exhibits significant advantages over the baseline model in two key evaluation metrics, hit rate and normalized discount cumulative gain (NDCG), on the MOOC platform and other datasets. Specifically, hit rate and NDCG improved by 13% vs. 9.8% and 15.7% vs. 12.8% when Top-k was set to 10 and 20, respectively.https://www.aimspress.com/article/doi/10.3934/era.2025053neural collaborative filteringmulti-head attention mechanismimplicit feedbackmultiple attention force mechanismsscore prediction
spellingShingle Hui Li
Shuai Wu
Ronghui Wang
Wenbin Hu
Haining Li
Modeling and application of implicit feedback in personalized recommender systems
Electronic Research Archive
neural collaborative filtering
multi-head attention mechanism
implicit feedback
multiple attention force mechanisms
score prediction
title Modeling and application of implicit feedback in personalized recommender systems
title_full Modeling and application of implicit feedback in personalized recommender systems
title_fullStr Modeling and application of implicit feedback in personalized recommender systems
title_full_unstemmed Modeling and application of implicit feedback in personalized recommender systems
title_short Modeling and application of implicit feedback in personalized recommender systems
title_sort modeling and application of implicit feedback in personalized recommender systems
topic neural collaborative filtering
multi-head attention mechanism
implicit feedback
multiple attention force mechanisms
score prediction
url https://www.aimspress.com/article/doi/10.3934/era.2025053
work_keys_str_mv AT huili modelingandapplicationofimplicitfeedbackinpersonalizedrecommendersystems
AT shuaiwu modelingandapplicationofimplicitfeedbackinpersonalizedrecommendersystems
AT ronghuiwang modelingandapplicationofimplicitfeedbackinpersonalizedrecommendersystems
AT wenbinhu modelingandapplicationofimplicitfeedbackinpersonalizedrecommendersystems
AT hainingli modelingandapplicationofimplicitfeedbackinpersonalizedrecommendersystems