Personalized recommendation model with multi-level latent features
Personalized recommendation has become one of the most effective means to solve information overload, and it is also a hot technology in the research field of massive data mining.However, traditional recommendation algorithms often only use the user’s rating information on the item, and lack a compr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2022-02-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022035/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529027898114048 |
|---|---|
| author | Qing SHEN Wenbin GUO Jungang LOU Qiangguo YU |
| author_facet | Qing SHEN Wenbin GUO Jungang LOU Qiangguo YU |
| author_sort | Qing SHEN |
| collection | DOAJ |
| description | Personalized recommendation has become one of the most effective means to solve information overload, and it is also a hot technology in the research field of massive data mining.However, traditional recommendation algorithms often only use the user’s rating information on the item, and lack a comprehensive consideration of the potential characteristics of the user and the item.The factorization machine, wide neural network, crossover network and deep neural network were combined to extract the shallow latent features, low-order nonlinear latent features, linear cross latent features, and high-order nonlinear latent features of users and items.Thus, a new deep learning personalized recommendation model with multilevel latent features was established.The experimental results on four commonly used data sets show that considering the multi-level potential features of users and items can effectively improve the prediction accuracy of personalized recommendations.Finally, the influence of factors such as the dimensions of the embedding layer and the number of neurons on the prediction performance of the new model was studied. |
| format | Article |
| id | doaj-art-86718411c02948a79445c73458c9960e |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2022-02-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-86718411c02948a79445c73458c9960e2025-01-15T03:26:41ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012022-02-0138718359809416Personalized recommendation model with multi-level latent featuresQing SHENWenbin GUOJungang LOUQiangguo YUPersonalized recommendation has become one of the most effective means to solve information overload, and it is also a hot technology in the research field of massive data mining.However, traditional recommendation algorithms often only use the user’s rating information on the item, and lack a comprehensive consideration of the potential characteristics of the user and the item.The factorization machine, wide neural network, crossover network and deep neural network were combined to extract the shallow latent features, low-order nonlinear latent features, linear cross latent features, and high-order nonlinear latent features of users and items.Thus, a new deep learning personalized recommendation model with multilevel latent features was established.The experimental results on four commonly used data sets show that considering the multi-level potential features of users and items can effectively improve the prediction accuracy of personalized recommendations.Finally, the influence of factors such as the dimensions of the embedding layer and the number of neurons on the prediction performance of the new model was studied.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022035/personalized recommendationhierarchical latent featuredeep learning |
| spellingShingle | Qing SHEN Wenbin GUO Jungang LOU Qiangguo YU Personalized recommendation model with multi-level latent features Dianxin kexue personalized recommendation hierarchical latent feature deep learning |
| title | Personalized recommendation model with multi-level latent features |
| title_full | Personalized recommendation model with multi-level latent features |
| title_fullStr | Personalized recommendation model with multi-level latent features |
| title_full_unstemmed | Personalized recommendation model with multi-level latent features |
| title_short | Personalized recommendation model with multi-level latent features |
| title_sort | personalized recommendation model with multi level latent features |
| topic | personalized recommendation hierarchical latent feature deep learning |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022035/ |
| work_keys_str_mv | AT qingshen personalizedrecommendationmodelwithmultilevellatentfeatures AT wenbinguo personalizedrecommendationmodelwithmultilevellatentfeatures AT junganglou personalizedrecommendationmodelwithmultilevellatentfeatures AT qiangguoyu personalizedrecommendationmodelwithmultilevellatentfeatures |