Fashion Outfit Generation for E-commerce
This addresses the need for scalable and personalized outfit recommendations in fashion retail, replacing manual processes by expert stylists.
The paper tackled the problem of automatically generating compatible fashion outfits for e-commerce by learning item embeddings in a latent style space using a neural network with visual and textual features, resulting in user approval rates 21% and 34% higher than a baseline for womenswear and menswear, respectively.
Combining items of clothing into an outfit is a major task in fashion retail. Recommending sets of items that are compatible with a particular seed item is useful for providing users with guidance and inspiration, but is currently a manual process that requires expert stylists and is therefore not scalable or easy to personalise. We use a multilayer neural network fed by visual and textual features to learn embeddings of items in a latent style space such that compatible items of different types are embedded close to one another. We train our model using the ASOS outfits dataset, which consists of a large number of outfits created by professional stylists and which we release to the research community. Our model shows strong performance in an offline outfit compatibility prediction task. We use our model to generate outfits and for the first time in this field perform an AB test, comparing our generated outfits to those produced by a baseline model which matches appropriate product types but uses no information on style. Users approved of outfits generated by our model 21% and 34% more frequently than those generated by the baseline model for womenswear and menswear respectively.