Hierarchical User Profiling for E-commerce Recommender Systems

被引:64
作者
Gu, Yulong [1 ]
Ding, Zhuoye [1 ]
Wang, Shuaiqiang [1 ]
Yin, Dawei [1 ]
机构
[1] JD Com, Data Sci Lab, Beijing, Peoples R China
来源
PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM '20) | 2020年
关键词
User profiling; Recommender systems; Hierarchical user profiling; Pyramid Recurrent Neural Networks; E-commerce;
D O I
10.1145/3336191.3371827
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Hierarchical user profiling that aims to model users' real-time interests in different granularity is an essential issue for personalized recommendations in E-commerce. On one hand, items (i.e. products) are usually organized hierarchically in categories, and correspondingly users' interests are naturally hierarchical on different granularity of items and categories. On the other hand, multiple granularity oriented recommendations become very popular in E-commerce sites, which require hierarchical user profiling in different granularity as well. In this paper, we propose HUP, a Hierarchical User Profiling framework to solve the hierarchical user profiling problem in E-commerce recommender systems. In HUP, we provide a Pyramid Recurrent Neural Networks, equipped with Behavior-LSTM to formulate users' hierarchical real-time interests at multiple scales. Furthermore, instead of simply utilizing users' item-level behaviors (e.g., ratings or clicks) in conventional methods, HUP harvests the sequential information of users' temporal finely-granular interactions (micro-behaviors, e.g., clicks on components of items like pictures or comments, browses with navigation of the search engines or recommendations) for modeling. Extensive experiments on two real-world E-commerce datasets demonstrate the significant performance gains of the HUP against state-of-the-art methods for the hierarchical user profiling and recommendation problems.
引用
收藏
页码:223 / 231
页数:9
相关论文
共 45 条
[31]   Item Recommendation on Monotonic Behavior Chains [J].
Wan, Mengting ;
McAuley, Julian .
12TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS), 2018, :86-94
[32]   A Path-constrained Framework for Discriminating Substitutable and Complementary Products in E-commerce [J].
Wang, Zihan ;
Jiang, Ziheng ;
Ren, Zhaochun ;
Tang, Jiliang ;
Yin, Dawei .
WSDM'18: PROCEEDINGS OF THE ELEVENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2018, :619-627
[33]   Recurrent Recommender Networks [J].
Wu, Chao-Yuan ;
Ahmed, Amr ;
Beutel, Alex ;
Smola, Alexander J. ;
Jing, How .
WSDM'17: PROCEEDINGS OF THE TENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2017, :495-503
[34]  
Zhao Xu, 2019, arXiv
[35]   Deep Reinforcement Learning for Page-wise Recommendations [J].
Zhao, Xiangyu ;
Xia, Long ;
Zhang, Liang ;
Ding, Zhuoye ;
Yin, Dawei ;
Tang, Jiliang .
12TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS), 2018, :95-103
[36]   Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning [J].
Zhao, Xiangyu ;
Zhang, Liang ;
Ding, Zhuoye ;
Xia, Long ;
Tang, Jiliang ;
Yin, Dawei .
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :1040-1048
[37]   Improving User Topic Interest Profiles by Behavior Factorization [J].
Zhao, Zhe ;
Cheng, Zhiyuan ;
Hong, Lichan ;
Chi, Ed H. .
PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW 2015), 2015, :1406-1416
[38]  
Zhou GR, 2019, AAAI CONF ARTIF INTE, P5941
[39]   Deep Interest Network for Click-Through Rate Prediction [J].
Zhou, Guorui ;
Zhu, Xiaoqiang ;
Song, Chengru ;
Fan, Ying ;
Zhu, Han ;
Ma, Xiao ;
Yan, Yanghui ;
Jin, Junqi ;
Li, Han ;
Gai, Kun .
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :1059-1068
[40]   Micro Behaviors: A New Perspective in E-commerce Recommender Systems [J].
Zhou, Meizi ;
Ding, Zhuoye ;
Tang, Jiliang ;
Yin, Dawei .
WSDM'18: PROCEEDINGS OF THE ELEVENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2018, :727-735