Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems

Fashion industry is driven by fashion cycles, in which a fashion item is launched, rises to mainstream appeal and becomes a trend, then diminishes and eventually becomes obsolete. These properties make it critical to incorporate temporal information when adapting a recommendation framework to be emp...

Full description

Saved in:
Bibliographic Details
Main Authors: Aayush Singha Roy, Edoardo D'Amico, Aonghus Lawlor, Neil Hurley
Format: Article
Language:English
Published: LibraryPress@UF 2023-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/133307
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762915611049984
author Aayush Singha Roy
Edoardo D'Amico
Aonghus Lawlor
Neil Hurley
author_facet Aayush Singha Roy
Edoardo D'Amico
Aonghus Lawlor
Neil Hurley
author_sort Aayush Singha Roy
collection DOAJ
description Fashion industry is driven by fashion cycles, in which a fashion item is launched, rises to mainstream appeal and becomes a trend, then diminishes and eventually becomes obsolete. These properties make it critical to incorporate temporal information when adapting a recommendation framework to be employed in the fashion domain. However, an industry standard real-world recommendation architecture entails numerous phases, including data preparation, establishing and training recommender models, filtering and fulfilling revenue-based user needs. The contributions of the presented work are twofold. We first formalise the multi-stage recommendation pipeline by including the time dimension intrinsically present in the fashion data. We then present a study to incorporate explicit fashion domain characteristics into the presented pipeline. Finally, we conduct comprehensive experimentation on a real-world web-scale fashion dataset released by H\&M, illustrating how including domain knowledge in the multi-stage framework can lead to significantly improvement on the final recommendation performance.
format Article
id doaj-art-41705c0446614f1bbf107bc6031a5dda
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2023-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-41705c0446614f1bbf107bc6031a5dda2025-08-20T03:05:35ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622023-05-013610.32473/flairs.36.13330769613Addressing Fast Changing Fashion Trends in Multi-Stage Recommender SystemsAayush Singha Roy0https://orcid.org/0009-0000-7085-3306Edoardo D'Amico1https://orcid.org/0000-0002-8262-7207Aonghus Lawlor2https://orcid.org/0000-0002-6160-4639Neil Hurley3https://orcid.org/0000-0001-8428-2866University College of Dublin and Insight Centre for Data AnalyticsUniversity College of Dublin and Insight Centre for Data AnalyticsUniversity College of Dublin and Insight Centre for Data AnalyticsUniversity College of Dublin and Insight Centre for Data AnalyticsFashion industry is driven by fashion cycles, in which a fashion item is launched, rises to mainstream appeal and becomes a trend, then diminishes and eventually becomes obsolete. These properties make it critical to incorporate temporal information when adapting a recommendation framework to be employed in the fashion domain. However, an industry standard real-world recommendation architecture entails numerous phases, including data preparation, establishing and training recommender models, filtering and fulfilling revenue-based user needs. The contributions of the presented work are twofold. We first formalise the multi-stage recommendation pipeline by including the time dimension intrinsically present in the fashion data. We then present a study to incorporate explicit fashion domain characteristics into the presented pipeline. Finally, we conduct comprehensive experimentation on a real-world web-scale fashion dataset released by H\&M, illustrating how including domain knowledge in the multi-stage framework can lead to significantly improvement on the final recommendation performance.https://journals.flvc.org/FLAIRS/article/view/133307multi-stage recommender systemsfashion recommendationlearning to rank
spellingShingle Aayush Singha Roy
Edoardo D'Amico
Aonghus Lawlor
Neil Hurley
Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems
Proceedings of the International Florida Artificial Intelligence Research Society Conference
multi-stage recommender systems
fashion recommendation
learning to rank
title Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems
title_full Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems
title_fullStr Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems
title_full_unstemmed Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems
title_short Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems
title_sort addressing fast changing fashion trends in multi stage recommender systems
topic multi-stage recommender systems
fashion recommendation
learning to rank
url https://journals.flvc.org/FLAIRS/article/view/133307
work_keys_str_mv AT aayushsingharoy addressingfastchangingfashiontrendsinmultistagerecommendersystems
AT edoardodamico addressingfastchangingfashiontrendsinmultistagerecommendersystems
AT aonghuslawlor addressingfastchangingfashiontrendsinmultistagerecommendersystems
AT neilhurley addressingfastchangingfashiontrendsinmultistagerecommendersystems