A Dataset for Adapting Recommender Systems to the Fashion Rental Economy

Karl Audun Kagnes Borgersen, Morten Goodwin, Jivitesh Sharma, Morten Grundetjern

Abstract:

In response to the escalating ecological challenges that threaten
global sustainability, there’s a deep need to investigate alternative
methods of commerce, such as rental economies. Like most online
commerce, rental or otherwise, a functioning recommender sys-
tem is crucial for their success. Yet the domain has, until this point,
been largely neglected by the recommender system research com-
munity.
Our dataset, derived from our collaboration with the leading
Norwegian fashion rental company Vibrent, encompasses 64𝑘 trans-
actions, rental histories from 2.2𝑘 anonymized users, and 15.8𝑘
unique outfits in which each physical item’s attributes and rental
history is meticulously tracked. All outfits are listed as individual
items or their corresponding item groups, referring to shared de-
signs between the individual items. This approach underlines the
novel challenges of rental as compared to more traditional recom-
mender system problems where items are generally interchange-
able. Each outfit is accompanied by a set of tags describing some
of their attributes. We also provide a total of 50𝑘 images displaying
across all items along with a set of precomputed zero-shot embed-
dings.
We apply a myriad of common recommender system methods to
the dataset to provide a performance baseline. This baseline is cal-
culated for the traditional fashion recommender system problem of
recommending outfit groups and the novel problem of predicting
individual item rental. To our knowledge, this is the first published
article to directly discuss fashion rental recommender systems, as
well as the first published dataset intended for this purpose. It is
our hope that the publication of this dataset will serve as a catalyst
for a new branch of research for specialized fashion rental recom-
mender systems.