Building A Non-Personalized Recommender System by Learning Product and Basket Representation

Basit Öğe Kaydı
dc.authorwosidYILDIRIM, SAHIN/A-4345-2019
dc.contributor.authorYildirim, Savas
dc.contributor.authorSoyler, Sebnem Gunes
dc.contributor.authorAkarsu, Ozgur
dc.date.accessioned2024-07-18T20:47:19Z
dc.date.available2024-07-18T20:47:19Z
dc.date.issued2020
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description8th IEEE International Conference on Big Data (Big Data) -- DEC 10-13, 2020 -- ELECTR NETWORKen_US
dc.description.abstractIn this paper, we addressed the problem of learning product and basket representation for a non-personalized recommendation system where the baskets do not have a specific owner. The recommendation models tend to exploit as much information as possible along with basket patterns to improve performance. We focus on the representation problem for the baskets without any customer information. Deep learning-based architectures have solved many representation problems such as natural language processing (NLP) and computer vision (CV) so far. While the NLP model takes a bag of words as input, the recommendation models take a basket of products as input. The learning algorithm uses co-occurrence information and therefore exploits the idea that the things that appear in a similar environment share similar meaning. But traditional representation approaches such as one-hot encoding have dimensionality problems when the number of entities increases. On the other hand, neural models can solve this dimensionality curse and transform each entity into a short and dense vector, namely embeddings. We successfully designed unsupervised and supervised architectures to solve the product and basket embeddings for a recommendation engine. Our experiments show that the proposed deep learning architecture showed better performance than baseline approaches in terms of many metrics. We also discussed and addressed many product representation related problems throughout the paper.en_US
dc.description.sponsorshipIEEE,IEEE Comp Soc,IBM,Ankuraen_US
dc.description.sponsorshipKocSistem Information and Communication Services Inc.; Scientific and Technological Research Council of Turkey (TUBITAK) under European Union [9170063, PAPUD 16037]; Istanbul Bilgi University; KocSistem Information and Communication Services Incen_US
dc.description.sponsorshipThe study is funded by KocSistem Information and Communication Services Inc. and the Scientific and Technological Research Council of Turkey (TUBITAK Grant no: Grant No 9170063) under European Union EUREKA ITEA labelled (ITEA 3 Call3 PAPUD 16037 Project) R&D project. We would also like to thank KocSistem Information and Communication Services Inc for their funding and supporting the study. Finally, We would like to thank Istanbul Bilgi University for their support during this study.en_US
dc.identifier.doi10.1109/BigData50022.2020.9377963
dc.identifier.endpage4455en_US
dc.identifier.isbn978-1-7281-6251-5
dc.identifier.issn2639-1589
dc.identifier.scopus2-s2.0-85103833343en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage4450en_US
dc.identifier.urihttps://doi.org/10.1109/BigData50022.2020.9377963
dc.identifier.urihttps://hdl.handle.net/11411/7772
dc.identifier.wosWOS:000662554704065en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartof2020 Ieee International Conference on Big Data (Big Data)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectRepresentation Learningen_US
dc.subjectRecommendation Systemsen_US
dc.subjectDeep Learningen_US
dc.titleBuilding A Non-Personalized Recommender System by Learning Product and Basket Representationen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications