Home // DATA ANALYTICS 2022, The Eleventh International Conference on Data Analytics // View article

Towards Style Classification for Fashion Recommender Systems

Authors:
René Kessler
Jorge Marx Gómez

Keywords: E-Commerce, Recommender Systems, Style Classification, Deep Learning, Explainable AI

Abstract:
In recommender systems, products can be recommended based on customer modeling. Especially in fashion ecommerce, recommendations can be a solution for many business and sustainability challenges. This paper presents how deep learning can be used for style classification in fashion ecommerce. The style of a person is classified based on a photo. Furthermore, this paper analyzes which data preprocessing and augmentation techniques can positively impact a style classification model. In order to be able to explain recommendations based on this, it was analyzed to what extent the resulting model provides accurate results and the predictions can be explained.

Pages: 49 to 54

Copyright: Copyright (c) IARIA, 2022

Publication date: November 13, 2022

Published in: conference

ISSN: 2308-4464

ISBN: 978-1-61208-994-2

Location: Valencia, Spain

Dates: from November 13, 2022 to November 17, 2022