Expert and community based style advice

We propose a knowledge framework for garment recommendations, which is based on two pillars. The first pillar incorporates knowledge about aspects of fashion, such as materials, garments, colours, body types, facial features, social occasion etc., as well as their interrelations, with the purpose of providing personalised recommendations. The said knowledge is encoded in the form of an owl ontology, the origin of which is attributed to fashion experts. Moreover, in commercial fashion sites, customers purchase garments of various types. Because of that, interesting patterns in their purchase behaviour can be sought, and thus groups of garments that tend to be purchased together can be discovered. This forms the second pillar, that can be used to enhance the first pillar with community based garment recommendations. This paper is the description and integration of the aforementioned pillars in a knowledge framework.

► We defined an OWL ontology for garment recommendations.
► The ontology includes user stereotypes, defined by experts.
► The ontology is enriched with data-mined garment-centred communities.
► Inferencing provides the recommended garment given a body type or an occasion.
► Recommendation scheme combines experts’ knowledge with user interaction data.