Senior Data Scientist
Tech / Sizing
Fashion is a way to express identity, moods, and opinions and recent studies have shown that size and fit are among factors that overall influence customer satisfaction the most when buying online. A crucial difference when engaging in online fashion shopping is the lack of immediate sensory feedback about fit and feel of an article through touch and visual cues. For many, this serves as a major deterrent against fashion e-commerce.
To support customers in their buying journey, Zalando has developed size advice products, among which the size recommender that preselects the best fitting size for a customer with a purchase history. To that end, we propose a hierarchical Bayesian approach that 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.