Personalized Fashion Sequential Recommendation with Visual Feature Based on Conditional Hierarchical VAE

With the increase of online shopping services, there has been much research on fashion item recommendation. Unlike standard recommendation systems, a recommendation for fashion items needs to take into account the context of the item IDs in the user behavior and that of the fashion-specific visual features such as color and design. In this study, we propose the conditional hierarchical variational auto-encoder (CHVAE) for extracting fashion-specific visual features, and construct a fashion item recommendation system based on it. CHVAE is an extension of VAE to enable conditional and hierarchical learning. It can capture the continuous latent space of color and design using item images and labels, and extract visual features for fashion recommendations. In our experiments, we show that the proposed method outperforms an extensive list of state-of-the-art sequential recommendation models and achieves the same or better performance as human stylists.