short-paper

Open access

Optimizing Similar Item Recommendations in a Semi-structured Marketplace to Maximize Conversion

Authors:

Paul WangAuthors Info & Claims

RecSys '16: Proceedings of the 10th ACM Conference on Recommender Systems

Pages 199 - 202

https://doi.org/10.1145/2959100.2959166

Published: 07 September 2016 Publication History

PDF eReader

Abstract

This paper tackles the problem of recommendations in eBay's large semi-structured marketplace. eBay's variable inventory and lack of structured information about listings makes traditional collaborative filtering algorithms difficult to use. We discuss how to overcome these data limitations to produce high quality recommendations in real time with a combination of a customized scalable architecture as well as a widely applicable machine learned ranking model. A pointwise ranking approach is utilized to reduce the ranking problem to a binary classification problem optimized on past user purchase behavior. We present details of a sampling strategy and feature engineering that have been critical to achieve a lift in both purchase through rate (PTR) and revenue.

Supplementary Material

MP4 File (p199.mp4)

Download
613.58 MB

References

[1]

Apache Spark, spark.apache.org/.

Google Scholar

[2]

D. Arya, V. Ha-Thuc, and S. Sinha. Personalized federated search at LinkedIn. In CIKM, 2015.

Digital Library

Google Scholar

[3]

Elasticsearch, www.elastic.co/products/elasticsearch.

Google Scholar

[4]

A. Freno et al. One-pass ranking models for low-latency product recommendations. In SIGKDD, 2015.

Digital Library

Google Scholar

[5]

D. Goldberg, D. Nichols, B. M. Oki, and D. Terry. Using collaborative filtering to weave an information tapestry. Commun. ACM, 35(12):61--70, Dec. 1992.

Digital Library

Google Scholar

[6]

Lambda Architecture, lambda-architecture.net/.

Google Scholar

[7]

P. Li, Q. Wu, and C. J. Burges. Mcrank: Learning to rank using multiple classification and gradient boosting. In NIPS, pages 897--904, 2007.

Digital Library

Google Scholar

[8]

G. Linden, B. Smith, and J. York. Amazon.com recommendations: Item-to-item collaborative filtering. Internet Computing, IEEE, 7(1):76--80, 2003.

Digital Library

Google Scholar

[9]

T.-Y. Liu. Learning to rank for information retrieval. Foundations and Trends in Information Retrieval, 3(3):225--331, 2009.

Digital Library

Google Scholar

[10]

B. Sarwar et al. Item-based collaborative filtering recommendation algorithms. In WWW, 2001.

Digital Library

Google Scholar

[11]

H. Steck. Gaussian ranking by matrix factorization. In RecSys, pages 115--122, 2015.

Digital Library

Google Scholar

[12]

J. Weston et al. Learning to rank recommendations with the k-order statistic loss. In RecSys, 2013.

Digital Library

Google Scholar

Cited By

View all

Shah CWhite RThomas PMitra BSarkar SBelkin N(2023)Taking Search to TaskProceedings of the 2023 Conference on Human Information Interaction and Retrieval10.1145/3576840.3578288(1-13)Online publication date: 19-Mar-2023
https://dl.acm.org/doi/10.1145/3576840.3578288
Bibas KSar Shalom OJannach D(2023)Semi-supervised Adversarial Learning for Complementary Item RecommendationProceedings of the ACM Web Conference 202310.1145/3543507.3583462(1804-1812)Online publication date: 30-Apr-2023
https://dl.acm.org/doi/10.1145/3543507.3583462
Giahi RMaragheh RFarrokhsiar NXu JCho JKorpeoglu EKumar SAchan K(2023)GNN-GMVO: Graph Neural Networks for Optimizing Gross Merchandise Value in Similar Item Recommendation2023 IEEE International Conference on Data Mining Workshops (ICDMW)10.1109/ICDMW60847.2023.00189(1484-1492)Online publication date: 4-Dec-2023
https://doi.org/10.1109/ICDMW60847.2023.00189
Show More Cited By

Index Terms

Optimizing Similar Item Recommendations in a Semi-structured Marketplace to Maximize Conversion
1. Information systems
  1. Information retrieval
    1. Retrieval models and ranking

Recommendations

Generating Items Recommendations by Fusing Content and User-Item based Collaborative Filtering
Abstract
Nowadays e-commerce has spread all over the world. The e-shops are not similar to the physical shops. The e-shops can have hundreds or thousands of items independent of physical boundaries. The information about all these products is available on ...
Promoting Tail Item Recommendations in E-Commerce
UMAP '23: Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization

The research area of recommender systems (RS) in e-commerce has become extremely popular in recent years. However, traditional RSs tend to recommend popular items, while niche (long-tail) items are often neglected, which is known as the long-tail ...
Item cold-start recommendations: learning local collective embeddings
RecSys '14: Proceedings of the 8th ACM Conference on Recommender systems

Recommender systems suggest to users items that they might like (e.g., news articles, songs, movies) and, in doing so, they help users deal with information overload and enjoy a personalized experience. One of the main problems of these systems is the ...

Comments

Information & Contributors

Information

Published In

RecSys '16: Proceedings of the 10th ACM Conference on Recommender Systems

September 2016

490 pages

ISBN:9781450340359

DOI:10.1145/2959100

General Chairs:
Shilad Sen
Macalester College, USA
,
Werner Geyer
IBM Research Cambridge, USA
,
Program Chairs:
Jill Freyne
CSIRO, Australia
,
Pablo Castells
Universidad Autónoma de Madrid, Spain

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

In-Cooperation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 September 2016

Check for updates

Author Tags

Qualifiers

Short-paper

Conference

RecSys '16

Sponsor:

SIGCHI

RecSys '16: Tenth ACM Conference on Recommender Systems

September 15 - 19, 2016

Massachusetts, Boston, USA

Acceptance Rates

RecSys '16 Paper Acceptance Rate 29 of 159 submissions, 18%;

Overall Acceptance Rate 254 of 1,295 submissions, 20%

Upcoming Conference

RecSys '24

Sponsor:
sigchi

18th ACM Conference on Recommender Systems

October 14 - 18, 2024

Bari , Italy

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

23
Total Citations
View Citations
4,956
Total Downloads

Downloads (Last 12 months)1,879
Downloads (Last 6 weeks)73

Reflects downloads up to 03 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Shah CWhite RThomas PMitra BSarkar SBelkin N(2023)Taking Search to TaskProceedings of the 2023 Conference on Human Information Interaction and Retrieval10.1145/3576840.3578288(1-13)Online publication date: 19-Mar-2023
https://dl.acm.org/doi/10.1145/3576840.3578288
Bibas KSar Shalom OJannach D(2023)Semi-supervised Adversarial Learning for Complementary Item RecommendationProceedings of the ACM Web Conference 202310.1145/3543507.3583462(1804-1812)Online publication date: 30-Apr-2023
https://dl.acm.org/doi/10.1145/3543507.3583462
Giahi RMaragheh RFarrokhsiar NXu JCho JKorpeoglu EKumar SAchan K(2023)GNN-GMVO: Graph Neural Networks for Optimizing Gross Merchandise Value in Similar Item Recommendation2023 IEEE International Conference on Data Mining Workshops (ICDMW)10.1109/ICDMW60847.2023.00189(1484-1492)Online publication date: 4-Dec-2023
https://doi.org/10.1109/ICDMW60847.2023.00189
Werneck HSilva NMito CPereira ADias DAlbergaria ERocha L(2022)Introducing Contextual Information in an Ensemble Recommendation System for Fashion DomainsProceedings of the Brazilian Symposium on Multimedia and the Web10.1145/3539637.3557058(222-229)Online publication date: 7-Nov-2022
https://dl.acm.org/doi/10.1145/3539637.3557058
Balashankar AFraiberger SDeregt EGorgens MSubramanian L(2022)Targeted Policy Recommendations using Outcome-aware ClusteringProceedings of the 5th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies10.1145/3530190.3534797(300-312)Online publication date: 29-Jun-2022
https://dl.acm.org/doi/10.1145/3530190.3534797
Mim NNandi DKhan SDey A(2022)F-commerce and Urban Modernities: The Changing Terrain of Housing Design in BangladeshProceedings of the 2022 CHI Conference on Human Factors in Computing Systems10.1145/3491102.3502071(1-20)Online publication date: 29-Apr-2022
https://dl.acm.org/doi/10.1145/3491102.3502071
Rome SHamidian SWalsh RFoley KTure FAmigo ECastells PGonzalo JCarterette BCulpepper JKazai G(2022)Learning to Rank Instant Search Results with Multiple IndicesProceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3477495.3536334(3412-3416)Online publication date: 6-Jul-2022
https://dl.acm.org/doi/10.1145/3477495.3536334
Matsui RYaginuma SNaito TNakata K(2022)Noise–Robust Sampling for Collaborative Metric LearningThe Review of Socionetwork Strategies10.1007/s12626-022-00131-x16:2(307-332)Online publication date: 9-Oct-2022
https://doi.org/10.1007/s12626-022-00131-x
Jesse MBauer CJannach D(2022)Intra-list similarity and human diversity perceptions of recommendations: the details matterUser Modeling and User-Adapted Interaction10.1007/s11257-022-09351-w33:4(769-802)Online publication date: 12-Dec-2022
https://doi.org/10.1007/s11257-022-09351-w
Werneck HSilva NMito CPereira ATuler EDias DRocha L(2022)A Stacking Recommender System Based on Contextual Information for Fashion RetailsComputational Science and Its Applications – ICCSA 202210.1007/978-3-031-10522-7_38(560-574)Online publication date: 15-Jul-2022
https://doi.org/10.1007/978-3-031-10522-7_38
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Generating Items Recommendations by Fusing Content and User-Item based Collaborative Filtering

Promoting Tail Item Recommendations in E-Commerce

Item cold-start recommendations: learning local collective embeddings