Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.14/41433 |
Resumo: | The fashion e-commerce market has experienced a significant growth and more and more customers tend to buy products online, rather than in physical stores. However, after a customer buys a product online, only a fraction of the garments stay in their wardrobe as many items are being returned to the vendor. Due to the absence of physical examination and misleading product descriptions customers struggle to find the right product suitable to their personal preferences. Especially the category of women’s lingerie suffers to a great extend from high return rates. Different sources report that between 70 up to 100% of women wear wrong sized bras. Personalized recommendations through so called recommendation systems play an essential role in e-commerce. This thesis aims to optimize the current product recommendations of a Belgium start-up called CurveCatch that sells women’s lingerie articles online and relies on a try-before-you-buy concept. To predict which products a customer is likely to buy two different personalized deep learning approaches were introduced. Data sparsity was addressed by labeling each unique product per customer and minority classes were synthetically oversampled. The findings demonstrated that recommendation systems are not only relevant for companies operating on a large scale. Rather, they also can be a valuable source of accurate recommendations for start-ups with sparse data. However, results also underlined well-known limitations of recommendation systems. Both models struggled especially when identifying products a customer is likely to buy, while it was rather easy to identify products a customer is not likely to buy. |
id |
RCAP_7746b0c5da4c34b46c7c0be992329bb4 |
---|---|
oai_identifier_str |
oai:repositorio.ucp.pt:10400.14/41433 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sitMachine learningRecommendation systemsDeep learningData sparsityFashione-CommerceProduct recommendationsAprendizagem de máquinasSistemas de recomendaçãoAprendizagem profundaEspaçamento de dadosModaRecomendações de produtosDomínio/Área Científica::Ciências Sociais::Economia e GestãoThe fashion e-commerce market has experienced a significant growth and more and more customers tend to buy products online, rather than in physical stores. However, after a customer buys a product online, only a fraction of the garments stay in their wardrobe as many items are being returned to the vendor. Due to the absence of physical examination and misleading product descriptions customers struggle to find the right product suitable to their personal preferences. Especially the category of women’s lingerie suffers to a great extend from high return rates. Different sources report that between 70 up to 100% of women wear wrong sized bras. Personalized recommendations through so called recommendation systems play an essential role in e-commerce. This thesis aims to optimize the current product recommendations of a Belgium start-up called CurveCatch that sells women’s lingerie articles online and relies on a try-before-you-buy concept. To predict which products a customer is likely to buy two different personalized deep learning approaches were introduced. Data sparsity was addressed by labeling each unique product per customer and minority classes were synthetically oversampled. The findings demonstrated that recommendation systems are not only relevant for companies operating on a large scale. Rather, they also can be a valuable source of accurate recommendations for start-ups with sparse data. However, results also underlined well-known limitations of recommendation systems. Both models struggled especially when identifying products a customer is likely to buy, while it was rather easy to identify products a customer is not likely to buy.O mercado de e-commerce de moda experimentou um crescimento significativo e cada vez mais os clientes tendem a comprar produtos online, em vez de em lojas físicas. No entanto, muitos itens são devolvidos ao vendedor após a compra online, pois os clientes têm dificuldade em encontrar o produto certo adequado às suas preferências pessoais devido à falta de exame físico e às descrições de produtos enganosas. A categoria de lingerie feminina sofre muito com as altas taxas de devolução. Diferentes fontes relatam que entre 70% e 100% das mulheres usam sutiãs do tamanho errado. As recomendações personalizadas através dos chamados sistemas de recomendação desempenham um papel essencial no e-commerce. Esta tese visa otimizar as atuais recomendações de produtos de uma start-up belga chamada CurveCatch que vende artigos de lingerie feminina online e depende de um conceito de experimente antes de comprar. Para prever quais produtos um cliente é mais propenso a comprar, foram introduzidos dois diferentes abordagens de aprendizado profundo personalizadas. A escassez de dados foi abordada rotulando cada produto único por cliente e as classes minoritárias foram sobreamostradas sinteticamente. Os resultados demonstraram que os sistemas de recomendação também podem ser uma fonte valiosa de recomendação de produtos para start-ups com dados escassos. No entanto, os resultados também sublinharam as bem conhecidas limitações dos sistemas de recomendação. Ambos os modelos lutaram especialmente ao identificar os produtos que um cliente é mais propenso a comprar, enquanto era relativamente fácil identificar os produtos que um cliente não é propenso a comprar.Gijsbrechts, JorenVeritati - Repositório Institucional da Universidade Católica PortuguesaRuh, Paul Johan2023-06-26T10:21:11Z2023-02-032023-012023-02-03T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.14/41433TID:203252772enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-12T17:47:00Zoai:repositorio.ucp.pt:10400.14/41433Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T18:34:07.587154Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
title |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
spellingShingle |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit Ruh, Paul Johan Machine learning Recommendation systems Deep learning Data sparsity Fashion e-Commerce Product recommendations Aprendizagem de máquinas Sistemas de recomendação Aprendizagem profunda Espaçamento de dados Moda Recomendações de produtos Domínio/Área Científica::Ciências Sociais::Economia e Gestão |
title_short |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
title_full |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
title_fullStr |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
title_full_unstemmed |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
title_sort |
Optimizing product recommendations for a try-before-you-buy fashion e-commerce sit |
author |
Ruh, Paul Johan |
author_facet |
Ruh, Paul Johan |
author_role |
author |
dc.contributor.none.fl_str_mv |
Gijsbrechts, Joren Veritati - Repositório Institucional da Universidade Católica Portuguesa |
dc.contributor.author.fl_str_mv |
Ruh, Paul Johan |
dc.subject.por.fl_str_mv |
Machine learning Recommendation systems Deep learning Data sparsity Fashion e-Commerce Product recommendations Aprendizagem de máquinas Sistemas de recomendação Aprendizagem profunda Espaçamento de dados Moda Recomendações de produtos Domínio/Área Científica::Ciências Sociais::Economia e Gestão |
topic |
Machine learning Recommendation systems Deep learning Data sparsity Fashion e-Commerce Product recommendations Aprendizagem de máquinas Sistemas de recomendação Aprendizagem profunda Espaçamento de dados Moda Recomendações de produtos Domínio/Área Científica::Ciências Sociais::Economia e Gestão |
description |
The fashion e-commerce market has experienced a significant growth and more and more customers tend to buy products online, rather than in physical stores. However, after a customer buys a product online, only a fraction of the garments stay in their wardrobe as many items are being returned to the vendor. Due to the absence of physical examination and misleading product descriptions customers struggle to find the right product suitable to their personal preferences. Especially the category of women’s lingerie suffers to a great extend from high return rates. Different sources report that between 70 up to 100% of women wear wrong sized bras. Personalized recommendations through so called recommendation systems play an essential role in e-commerce. This thesis aims to optimize the current product recommendations of a Belgium start-up called CurveCatch that sells women’s lingerie articles online and relies on a try-before-you-buy concept. To predict which products a customer is likely to buy two different personalized deep learning approaches were introduced. Data sparsity was addressed by labeling each unique product per customer and minority classes were synthetically oversampled. The findings demonstrated that recommendation systems are not only relevant for companies operating on a large scale. Rather, they also can be a valuable source of accurate recommendations for start-ups with sparse data. However, results also underlined well-known limitations of recommendation systems. Both models struggled especially when identifying products a customer is likely to buy, while it was rather easy to identify products a customer is not likely to buy. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-06-26T10:21:11Z 2023-02-03 2023-01 2023-02-03T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.14/41433 TID:203252772 |
url |
http://hdl.handle.net/10400.14/41433 |
identifier_str_mv |
TID:203252772 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799132067612590080 |