An AI pipeline for garment price projection using computer vision

Basit Öğe Kaydı
dc.contributor.authorRico Gómez R.
dc.contributor.authorLorentz J.
dc.contributor.authorHartmann T.
dc.contributor.authorGoknil A.
dc.contributor.authorPal Singh I.
dc.contributor.authorHalaç T.G.
dc.contributor.authorBoruzanlı Ekinci G.
dc.date.accessioned2024-08-31T07:42:24Z
dc.date.available2024-08-31T07:42:24Z
dc.date.issued2024
dc.departmentEge Üniversitesien_US
dc.description.abstractThe fashion industry’s traditional price-setting methods, based on historical sales and Fashion Week trends, are inadequate in the digital era. Rapid changes in collections and consumer preferences necessitate advanced Artificial Intelligence (AI) techniques. These AI methods should analyze data from various sources, including social media and e-commerce, to predict future fashion trends and prices. In this paper, we propose, apply, and assess a data analytics approach, i.e., FashionXpert, employing several image processing and machine learning techniques in an AI pipeline for garment price prediction. It integrates various heterogeneous data sources (e.g., textual and image data from e-stores, brand websites, and social media) to obtain more consistent, accurate, and beneficial information. We evaluated its effectiveness with an industrial data set obtained by a fashion search tool from the electronic commerce sites of clothing brands. FashionXpert predicted garment prices with an average Mean Absolute Error (MAE) of 15.31 EUR on a data set that has a standard deviation of 72.99 EUR. © The Author(s) 2024.en_US
dc.description.sponsorshipLuxembourg Ministry of Economy; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK, (119N537); Fonds National de la Recherche Luxembourg, FNR, (14297122)en_US
dc.identifier.doi10.1007/s00521-024-09901-w
dc.identifier.issn0941-0643
dc.identifier.scopus2-s2.0-85193233340en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org10.1007/s00521-024-09901-w
dc.identifier.urihttps://hdl.handle.net/11454/103850
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.relation.ispartofNeural Computing and Applicationsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.snmz20240831_Uen_US
dc.subjectImage segmentationen_US
dc.subjectMulti-label classificationen_US
dc.subjectPrice regressionen_US
dc.titleAn AI pipeline for garment price projection using computer visionen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu