Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems

Abstract

Fashion industry is driven by fashion cycles, in which a fashion item is launched, rises to mainstream appeal and becomes a trend, then diminishes and eventually becomes obsolete. These properties make it critical to incorporate temporal information when adapting a recommendation framework to be employed in the fashion domain. However, an industry standard real-world recommendation architecture entails numerous phases, including data preparation, establishing and training recommender models, filtering and fulfilling revenue-based user needs. The contributions of the presented work are twofold. We first formalise the multi-stage recommendation pipeline by including the time dimension intrinsically present in the fashion data. We then present a study to incorporate explicit fashion domain characteristics into the presented pipeline. Finally, we conduct comprehensive experimentation on a real-world web-scale fashion dataset released by H\&M, illustrating how including domain knowledge in the multi-stage framework can lead to significantly improvement on the final recommendation performance.