Sequence aware recommenders for fashion E-commerce

Abstract In recent years, fashion e-commerce has become more and more popular. Since there are so many fashion products provided by e-commerce retailers, it is necessary to provide recommendation services to users to minimize information overload. When users look for a product on an e-commerce website, they usually click the product information sequentially. Previous recommenders, such as content-based recommenders and collaborative filtering recommenders, do not consider this important behavioral characteristic. To take advantage of this important characteristic, this study proposes sequence-aware recommenders for fashion product recommendation using a gated recurrent unit (GRU) algorithm. We conducted an experiment using a dataset collected from an e-commerce website of a Korean fashion company. Experimental results show that sequence aware recommenders outperform non-sequence aware recommender, and multiple sequence-based recommenders outperform a single sequence-based recommender because they consider the attributes of fashion products. Finally, we discuss the implications of our study on fashion recommendations and propose further research topics.