Abstract

In recent years, product search engines have emerged as a key factor for online businesses. According to a recent survey, over 55% of online customers begin their online shopping journey by searching on an E-Commerce (EC) website like Amazon as opposed to a generic web search engine like Google. Information retrieval research to date has been focused on optimizing search ranking algorithms for web documents while little attention has been paid to product search. There are several intrinsic differences between web search and product search that make the direct application of traditional search ranking algorithms to EC search platforms difficult. First, the success of web and product search is measured differently; one seeks to optimize for relevance while the other must optimize for both relevance and revenue. Second, when using real-world EC transaction data, there is no access to manually annotated labels. In this paper, we address these differences with a novel learning framework for EC product search called LETORIF (LEarning TO Rank with Implicit Feedback). In this framework, we utilize implicit user feedback signals (such as user clicks and purchases) and jointly model the different stages of the shopping journey to optimize for EC sales revenue. We conduct experiments on real-world EC transaction data and introduce a a new evaluation metric to estimate expected revenue after re-ranking. Experimental results show that LETORIF outperforms top competitors in improving purchase rates and total revenue earned.

Original languageEnglish (US)
Title of host publication41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
PublisherAssociation for Computing Machinery, Inc
Pages365-374
Number of pages10
ISBN (Electronic)9781450356572
DOIs
StatePublished - Jun 27 2018
Event41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 - Ann Arbor, United States
Duration: Jul 8 2018Jul 12 2018

Other

Other41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
CountryUnited States
CityAnn Arbor
Period7/8/187/12/18

Fingerprint

Electronic commerce
Search engines
Feedback
Information retrieval
Labels
Websites
Sales
Industry
Experiments

Keywords

  • E-commerce
  • Revenue
  • Search logs

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design
  • Information Systems

Cite this

Wu, L., Hu, D., Hong, L., & Liu, H. (2018). Turning Clicks into purchases: Revenue optimization for product search in e-commerce. In 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 (pp. 365-374). Association for Computing Machinery, Inc. https://doi.org/10.1145/3209978.3209993

Turning Clicks into purchases : Revenue optimization for product search in e-commerce. / Wu, Liang; Hu, Diane; Hong, Liangjie; Liu, Huan.

41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018. Association for Computing Machinery, Inc, 2018. p. 365-374.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, L, Hu, D, Hong, L & Liu, H 2018, Turning Clicks into purchases: Revenue optimization for product search in e-commerce. in 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018. Association for Computing Machinery, Inc, pp. 365-374, 41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018, Ann Arbor, United States, 7/8/18. https://doi.org/10.1145/3209978.3209993
Wu L, Hu D, Hong L, Liu H. Turning Clicks into purchases: Revenue optimization for product search in e-commerce. In 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018. Association for Computing Machinery, Inc. 2018. p. 365-374 https://doi.org/10.1145/3209978.3209993
Wu, Liang ; Hu, Diane ; Hong, Liangjie ; Liu, Huan. / Turning Clicks into purchases : Revenue optimization for product search in e-commerce. 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018. Association for Computing Machinery, Inc, 2018. pp. 365-374
@inproceedings{82df6d1fa2b44d4a821bd04f8d5e9dde,
title = "Turning Clicks into purchases: Revenue optimization for product search in e-commerce",
abstract = "In recent years, product search engines have emerged as a key factor for online businesses. According to a recent survey, over 55{\%} of online customers begin their online shopping journey by searching on an E-Commerce (EC) website like Amazon as opposed to a generic web search engine like Google. Information retrieval research to date has been focused on optimizing search ranking algorithms for web documents while little attention has been paid to product search. There are several intrinsic differences between web search and product search that make the direct application of traditional search ranking algorithms to EC search platforms difficult. First, the success of web and product search is measured differently; one seeks to optimize for relevance while the other must optimize for both relevance and revenue. Second, when using real-world EC transaction data, there is no access to manually annotated labels. In this paper, we address these differences with a novel learning framework for EC product search called LETORIF (LEarning TO Rank with Implicit Feedback). In this framework, we utilize implicit user feedback signals (such as user clicks and purchases) and jointly model the different stages of the shopping journey to optimize for EC sales revenue. We conduct experiments on real-world EC transaction data and introduce a a new evaluation metric to estimate expected revenue after re-ranking. Experimental results show that LETORIF outperforms top competitors in improving purchase rates and total revenue earned.",
keywords = "E-commerce, Revenue, Search logs",
author = "Liang Wu and Diane Hu and Liangjie Hong and Huan Liu",
year = "2018",
month = "6",
day = "27",
doi = "10.1145/3209978.3209993",
language = "English (US)",
pages = "365--374",
booktitle = "41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Turning Clicks into purchases

T2 - Revenue optimization for product search in e-commerce

AU - Wu, Liang

AU - Hu, Diane

AU - Hong, Liangjie

AU - Liu, Huan

PY - 2018/6/27

Y1 - 2018/6/27

N2 - In recent years, product search engines have emerged as a key factor for online businesses. According to a recent survey, over 55% of online customers begin their online shopping journey by searching on an E-Commerce (EC) website like Amazon as opposed to a generic web search engine like Google. Information retrieval research to date has been focused on optimizing search ranking algorithms for web documents while little attention has been paid to product search. There are several intrinsic differences between web search and product search that make the direct application of traditional search ranking algorithms to EC search platforms difficult. First, the success of web and product search is measured differently; one seeks to optimize for relevance while the other must optimize for both relevance and revenue. Second, when using real-world EC transaction data, there is no access to manually annotated labels. In this paper, we address these differences with a novel learning framework for EC product search called LETORIF (LEarning TO Rank with Implicit Feedback). In this framework, we utilize implicit user feedback signals (such as user clicks and purchases) and jointly model the different stages of the shopping journey to optimize for EC sales revenue. We conduct experiments on real-world EC transaction data and introduce a a new evaluation metric to estimate expected revenue after re-ranking. Experimental results show that LETORIF outperforms top competitors in improving purchase rates and total revenue earned.

AB - In recent years, product search engines have emerged as a key factor for online businesses. According to a recent survey, over 55% of online customers begin their online shopping journey by searching on an E-Commerce (EC) website like Amazon as opposed to a generic web search engine like Google. Information retrieval research to date has been focused on optimizing search ranking algorithms for web documents while little attention has been paid to product search. There are several intrinsic differences between web search and product search that make the direct application of traditional search ranking algorithms to EC search platforms difficult. First, the success of web and product search is measured differently; one seeks to optimize for relevance while the other must optimize for both relevance and revenue. Second, when using real-world EC transaction data, there is no access to manually annotated labels. In this paper, we address these differences with a novel learning framework for EC product search called LETORIF (LEarning TO Rank with Implicit Feedback). In this framework, we utilize implicit user feedback signals (such as user clicks and purchases) and jointly model the different stages of the shopping journey to optimize for EC sales revenue. We conduct experiments on real-world EC transaction data and introduce a a new evaluation metric to estimate expected revenue after re-ranking. Experimental results show that LETORIF outperforms top competitors in improving purchase rates and total revenue earned.

KW - E-commerce

KW - Revenue

KW - Search logs

UR - http://www.scopus.com/inward/record.url?scp=85051504935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051504935&partnerID=8YFLogxK

U2 - 10.1145/3209978.3209993

DO - 10.1145/3209978.3209993

M3 - Conference contribution

AN - SCOPUS:85051504935

SP - 365

EP - 374

BT - 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018

PB - Association for Computing Machinery, Inc

ER -