A Practical Deep Online Ranking System in E-commerce Recommendation

被引：5

作者：

Yan, Yan ^{[1
]}

Liu, Zitao ^{[2
]}

Zhao, Meng ^{[1
]}

Guo, Wentao ^{[1
]}

Yan, Weipeng P. ^{[1
]}

Bao, Yongjun ^{[1
]}

机构：

[1] JDCOM, Intelligent Advertising Lab, 675 E Middlefield Rd, Mountain View, CA 94043 USA

[2] TAL Educ Grp, TAL AI Lab, Beijing, Peoples R China

来源：

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2018, PT III | 2019年 / 11053卷

关键词：

Recommender system; E-commerce; Deep learning; Multi-arm bandits;

D O I：

10.1007/978-3-030-10997-4_12

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

User online shopping experience in modern e-commerce websites critically relies on real-time personalized recommendations. However, building a productionized recommender system still remains challenging due to a massive collection of items, a huge number of online users, and requirements for recommendations to be responsive to user actions. In this work, we present our relevant, responsive, and scalable deep online ranking system (DORS) that we developed and deployed in our company. DORS is implemented in a three-level architecture which includes (1) candidate retrieval that retrieves a board set of candidates with various business rules enforced; (2) deep neural network ranking model that takes advantage of available user and item specific features and their interactions; (3) multi-arm bandits based online re-ranking that dynamically takes user real-time feedback and re-ranks the final recommended items in scale. Given a user as a query, DORS is able to precisely capture users' real-time purchasing intents and help users reach to product purchases. Both offline and online experimental results show that DORS provides more personalized online ranking results and makes more revenue.

引用

页码：186 / 201

页数：16

共 36 条

[1]

Agarwal Deepak, 2010, P 16 ACM SIGKDD INT, P703

[2]

[Anonymous], 2013, P 22 INT C WORLD WID

[3]

[Anonymous], 2010, ACM RecSys'10'

[4] Finite-time analysis of the multiarmed bandit problem [J].

Auer, P ;

Cesa-Bianchi, N ;

Fischer, P .

MACHINE LEARNING, 2002, 47 (2-3) :235-256

[5]

Awad M., 2015, Efficient learning machines: Theories, concepts, and applications for engineers and system designers, P67

[6]

Burges C., 2005, P 22 INT C MACH LEAR, P89, DOI DOI 10.1145/1102351.1102363

[7]

Cao Z., 2007, P 24 INT C MACH LEAR, P129, DOI [DOI 10.1145/1273496.1273513, 10.1145/1273496.1273513]

[8] Streaming Recommender Systems [J].

Chang, Shiyu ;

Zhang, Yang ;

Tang, Jiliang ;

Yin, Dawei ;

Chang, Yi ;

Hasegawa-Johnson, Mark A. ;

Huang, Thomas S. .

PROCEEDINGS OF THE 26TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW'17), 2017, :381-389

[9] TeRec: A Temporal Recommender System Over Tweet Stream [J].

Chen, Chen ;

Yin, Hongzhi ;

Yao, Junjie ;

Cui, Bin .

PROCEEDINGS OF THE VLDB ENDOWMENT, 2013, 6 (12) :1254-1257

[10] Practical selection of SVM parameters and noise estimation for SVM regression [J].

Cherkassky, V ;

Ma, YQ .

NEURAL NETWORKS, 2004, 17 (01) :113-126

← 1 2 3 4 →