A Hierarchical Bayesian Model for Size Recommendation in Fashion
This work addresses size recommendation for fashion e-commerce, which is an incremental improvement using a hierarchical Bayesian approach.
The authors tackled the problem of size recommendation in e-commerce fashion by developing a hierarchical Bayesian model that jointly predicts customer purchases and return events (no return, too small, or too big), with experiments conducted on anonymized data from millions of customers.
We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion. Our approach jointly models a size purchased by a customer, and its possible return event: 1. no return, 2. returned too small 3. returned too big. Those events are drawn following a multinomial distribution parameterized on the joint probability of each event, built following a hierarchy combining priors. Such a model allows us to incorporate extended domain expertise and article characteristics as prior knowledge, which in turn makes it possible for the underlying parameters to emerge thanks to sufficient data. Experiments are presented on real (anonymized) data from millions of customers along with a detailed discussion on the efficiency of such an approach within a large scale production system.