skip to main content
10.1145/3109859.3109891acmconferencesArticle/Chapter ViewAbstractPublication PagesrecsysConference Proceedingsconference-collections
research-article
Open access

Recommending Product Sizes to Customers

Published: 27 August 2017 Publication History

Abstract

We propose a novel latent factor model for recommending product size fits {Small, Fit, Large} to customers. Latent factors for customers and products in our model correspond to their physical true size, and are learnt from past product purchase and returns data. The outcome for a customer, product pair is predicted based on the difference between customer and product true sizes, and efficient algorithms are proposed for computing customer and product true size values that minimize two loss function variants. In experiments with Amazon shoe datasets, we show that our latent factor models incorporating personas, and leveraging return codes show a 17-21% AUC improvement compared to baselines. In an online A/B test, our algorithms show an improvement of 0.49% in percentage of Fit transactions over control.

References

[1]
Ruslan Salakhutdinov and Andriy Mnih. Probablistic Matrix Factorization. NIPS 2008.
[2]
Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix Factorization Techniques for Recommender Systems. IEEE Computer 2009.
[3]
P. K. Gopalan, L. Charlin, and D. Blei. Content-based recommendations with Poisson factorization.sayIn Advances in Neural Information Processing Systems, pages 3176--3184, 2014.
[4]
Dynamic Poisson Factorization, by Laurent Charlin, Rajesh Ranganath, James McInerney and David M. Blei, ACM Conference on Recommender Systems, Recsys 15
[5]
A Framework for Matrix Factorization based on General Distributions, by Josef Bauer and Alexandros Nanopoulos, ACM Conference on Recommender Systems, Recsys 14
[6]
Modeling the Dynamics of User Preferences in Coupled Tensor Factorization by Dimitrios Rafailidis and Alexandros Nanopoulos, ACM Conference on Recommender Systems, Recsys 14
[7]
Wei Chu and Seung-Taek Park. Personalized Recommendation on Dynamic Content Using Predictive Bilinear Models. WWW 2009.
[8]
Deepak Agarwal and Bee-Chung Chen. Regression based Latent Factor Models. KDD 2009.
[9]
Bayesian latent variable models for collaborative item rating prediction, Morgan Harvey, ACM International Conference on Information and Knowledge Management, CIKM 2011.
[10]
Bayesian probabilistic matrix factorization using Markov chain Monte Carlo, Ruslan Salakhutdinov, Andriy Mnih, International Conference on Machine Learning, ICML 2008.
[11]
Ling Li and Hsuan-Tien Lin. Ordinal Regression by Extended Binary Classification.Neural Information Processing Systems, NIPS 2006.
[12]
J. McAuley and J. Leskovec. Hidden factors and hiddentopics: understanding rating dimensions with review text. ACM Conference on Recommender Systems, Recsys 2013.
[13]
Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendationby Flavian Vasile, Elena Smirnova, Alexis Conneau, ACM Conference on Recommender Systems, Recsys 16
[14]
Asynchronous Distributed Matrix Factorization with Similar User and Item Based Regularization, Bikash Joshi, Franck Iutzeler, Massih-Reza Amini, ACM Conference on Recommender Systems, Recsys 16
[15]
Alexandros Karatzoglou, Xavier Amatriain, Linas Baltrunas, and Nuria Oliver. 2010. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems (RecSys '10). ACM, New York, NY, USA, 79--86.
[16]
Atsuhiro Narita, Kohei Hayashi, Ryota Tomioka, and Hisashi Kashima. 2011. Tensor factorization using auxiliary information. In Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part II (ECML PKDD'11), Dimitrios Gunopulos, Thomas Hofmann, Donato Malerba, and Michalis Vazirgiannis (Eds.), Vol. Part II. Springer-Verlag, Berlin, Heidelberg, 501--516.
[17]
Panniello, Umberto, et al. "Experimental comparison of pre-vs. post-filtering approaches in context-aware recommender systems." Proceedings of the third ACM conference on Recommender systems. ACM, 2009.
[18]
Adomavicius, Gediminas, and Alexander Tuzhilin. "Context-aware recommender systems." Recommender systems handbook. Springer US, 2015. 191--226.
[19]
Karen Church, Barry Smyth, Paul Cotter, and Keith Bradley. 2007. Mobile information access: A study of emerging search behavior on the mobile Internet. ACM Trans. Web 1, 1, Article 4 (May 2007).
[20]
Bradley, R. A. and Terry, M. E. (1952). Rank analysis of incomplete block designs, I. the method of paired comparisons. Biometrika, 39, 324--345.
[21]
Thurstone, L. L. (1959). The Measurement of Values. Chicago: The University of Chicago Press.

Cited By

View all

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
RecSys '17: Proceedings of the Eleventh ACM Conference on Recommender Systems
August 2017
466 pages
ISBN:9781450346528
DOI:10.1145/3109859
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License.

Sponsors

In-Cooperation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 August 2017

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. hinge loss
  2. latent factors
  3. ordinal loss
  4. personalization
  5. recommendation

Qualifiers

  • Research-article

Conference

RecSys '17
Sponsor:

Acceptance Rates

RecSys '17 Paper Acceptance Rate 26 of 125 submissions, 21%;
Overall Acceptance Rate 254 of 1,295 submissions, 20%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)145
  • Downloads (Last 6 weeks)18
Reflects downloads up to 06 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Efficiency a Key Enabler for Delivery Experience and ProfitabilityAI-Powered Ecommerce10.1007/979-8-8688-0923-1_8(203-232)Online publication date: 14-Dec-2024
  • (2024)Predicting Size and Fit in Fashion E-CommerceAdvances in Data and Information Sciences10.1007/978-981-99-6906-7_19(215-225)Online publication date: 3-Jan-2024
  • (2024)Personalized Novel Recommendation System Based on Filtering and Sentiment AnalysisData Science10.1007/978-981-97-8749-4_5(69-80)Online publication date: 31-Oct-2024
  • (2023)Analysis of RGB Depth Sensors on Fashion Dataset for Virtual Trial Room ImplementationResearch Trends in Artificial Intelligence: Internet of Things10.2174/9789815136449123010015(203-220)Online publication date: 21-Dec-2023
  • (2023)Computational Technologies for Fashion Recommendation: A SurveyACM Computing Surveys10.1145/362710056:5(1-45)Online publication date: 25-Nov-2023
  • (2023)Identification of Fine-Grained Fit Information from Customer Reviews in FashionRecommender Systems in Fashion and Retail10.1007/978-3-031-22192-7_1(1-23)Online publication date: 2-Mar-2023
  • (2022)FitGAN: Fit- and Shape-Realistic Generative Adversarial Networks for Fashion2022 26th International Conference on Pattern Recognition (ICPR)10.1109/ICPR56361.2022.9956089(3097-3104)Online publication date: 21-Aug-2022
  • (2022)Enhanced Movie Recommendation and Sentiment Analysis Model Achieved by Similarity Method through Cosine and Jaccard Similarity algorithms2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)10.1109/ICCCIS56430.2022.10037722(214-218)Online publication date: 4-Nov-2022
  • (2022)SkillSF: In the Sizing Game, Your Size is Your SkillRecommender Systems in Fashion and Retail10.1007/978-3-030-94016-4_4(49-61)Online publication date: 8-Mar-2022
  • (2022)Knowing When You Don’t Know in Online Fashion: An Uncertainty-Aware Size Recommendation FrameworkRecommender Systems in Fashion and Retail10.1007/978-3-030-94016-4_3(33-48)Online publication date: 8-Mar-2022
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media