Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank
In the past decade, recommender systems for e-commerce have witnessed significant advancement. Recommendation scenarios can be divided into different type (e.g., pre-, during-, post-purchase, campaign, promotion, bundle) for different user groups or different businesses. For different scenarios, the...
Saved in:
Main Authors: | , , , , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://ojs.aaai.org/index.php/AAAI/article/view/17785 https://hdl.handle.net/10356/152717 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-152717 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1527172021-09-29T03:09:26Z Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank Zeng, Anxiang Yu, Han He, Hualin Ni, Yabo Li, Yongliang Zhou, Jingren Miao, Chunyan School of Computer Science and Engineering Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) Alibaba-NTU Singapore Joint Research Institute Engineering::Computer science and engineering E-commerce Learning To Rank In the past decade, recommender systems for e-commerce have witnessed significant advancement. Recommendation scenarios can be divided into different type (e.g., pre-, during-, post-purchase, campaign, promotion, bundle) for different user groups or different businesses. For different scenarios, the goals of recommendation are different. This is reflected by the different performance metrics employed. In addition, online promotional campaigns, which attract high traffic volumes, are also a critical factor affecting e-commerce recommender systems. Typically, prior to a promotional campaign, the Add-to-Cart Rate (ACR) is the target of optimization. During the campaign, this changes to Gross Merchandise Volumes (GMV). Immediately after the campaign, it becomes Click Through Rates CTR. Dynamically adapting among these potentially conflicting optimization objectives is an important capability for recommender systems deployed in real-world e-commerce platforms. In this paper, we report our experience designing and deploying the Deep Controllable Learning-To-Rank (DC-LTR) recommender system to address this challenge. It enhances the feedback controller in LTR with multi-objective optimization so as to maximize different objectives under constraints. Its ability to dynamically adapt to changing business objectives has resulted in significant business advantages. Since September 2019, DC-LTR has become a core service enabling adaptive online training and real-time deployment ranking models based on changing business objectives in AliExpress and Lazada. Under both everyday use scenarios and peak load scenarios during large promotional campaigns, DC-LTR has achieved significant improvements in satisfying real-world business objectives. AI Singapore Nanyang Technological University National Research Foundation (NRF) Accepted version This research is supported, in part, by Alibaba Group through Alibaba Innovative Research (AIR) Program and Alibaba-NTU Singapore Joint Research Institute (JRI) (Alibaba-NTU-AIR2019B1), Nanyang Technological U- niversity, Singapore; the National Research Foundation, Singapore, under its AI Singapore Programme (AISG Award No: AISG-GC-2019-003); NRF Investigatorship Programme (NRFI Award No: NRF-NRFI05-2019-0002); Nanyang Assistant Professorship (NAP); the RIE 2020 Ad- vanced Manufacturing and Engineering (AME) Program- matic Fund (No. A20G8b0102), Singapore. 2021-09-29T02:50:30Z 2021-09-29T02:50:30Z 2021 Conference Paper Zeng, A., Yu, H., He, H., Ni, Y., Li, Y., Zhou, J. & Miao, C. (2021). Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 35, 15214-15222. 978-1-57735-866-4 2159-5399 https://ojs.aaai.org/index.php/AAAI/article/view/17785 https://hdl.handle.net/10356/152717 35 15214 15222 en Alibaba-NTU-AIR2019B1 AISG-GC-2019-003 NRF-NRFI05-2019-0002 A20G8b0102 © 2021 Association for the Advancement of Artificial Intelligence. All Rights Reserved. This paper was published in Proceedings of Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) and is made available with permission of Association for the Advancement of Artificial Intelligence. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering E-commerce Learning To Rank |
spellingShingle |
Engineering::Computer science and engineering E-commerce Learning To Rank Zeng, Anxiang Yu, Han He, Hualin Ni, Yabo Li, Yongliang Zhou, Jingren Miao, Chunyan Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank |
description |
In the past decade, recommender systems for e-commerce have witnessed significant advancement. Recommendation scenarios can be divided into different type (e.g., pre-, during-, post-purchase, campaign, promotion, bundle) for different user groups or different businesses. For different scenarios, the goals of recommendation are different. This is reflected by the different performance metrics employed. In addition, online promotional campaigns, which attract high traffic volumes, are also a critical factor affecting e-commerce recommender systems. Typically, prior to a promotional campaign, the Add-to-Cart Rate (ACR) is the target of optimization. During the campaign, this changes to Gross Merchandise Volumes (GMV). Immediately after the campaign, it becomes Click Through Rates CTR. Dynamically adapting among these potentially conflicting optimization objectives is an important capability for recommender systems deployed in real-world e-commerce platforms. In this paper, we report our experience designing and deploying the Deep Controllable Learning-To-Rank (DC-LTR) recommender system to address this challenge. It enhances the feedback controller in LTR with multi-objective optimization so as to maximize different objectives under constraints. Its ability to dynamically adapt to changing business objectives has resulted in significant business advantages. Since September 2019, DC-LTR has become a core service enabling adaptive online training and real-time deployment ranking models based on changing business objectives in AliExpress and Lazada. Under both everyday use scenarios and peak load scenarios during large promotional campaigns, DC-LTR has achieved significant improvements in satisfying real-world business objectives. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Zeng, Anxiang Yu, Han He, Hualin Ni, Yabo Li, Yongliang Zhou, Jingren Miao, Chunyan |
format |
Conference or Workshop Item |
author |
Zeng, Anxiang Yu, Han He, Hualin Ni, Yabo Li, Yongliang Zhou, Jingren Miao, Chunyan |
author_sort |
Zeng, Anxiang |
title |
Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank |
title_short |
Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank |
title_full |
Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank |
title_fullStr |
Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank |
title_full_unstemmed |
Enhancing e-commerce recommender system adaptability with online deep controllable Learning-To-Rank |
title_sort |
enhancing e-commerce recommender system adaptability with online deep controllable learning-to-rank |
publishDate |
2021 |
url |
https://ojs.aaai.org/index.php/AAAI/article/view/17785 https://hdl.handle.net/10356/152717 |
_version_ |
1712300648181006336 |