Footwear Size Recommendation System
This addresses the challenge of enhancing online shopping experiences for footwear customers by providing accurate size recommendations, though it appears incremental as it builds on prior work.
The paper tackles the problem of recommending shoe sizes for online shoppers, especially new users with no purchase history, by using a probabilistic approach based on user co-purchase data and a brand-brand relationship graph. It reports significant improvements in both recommendation precision and coverage compared to previous work.
While shopping for fashion products, customers usually prefer to try-out products to examine fit, material, overall look and feel. Due to lack of try out options during online shopping, it becomes pivotal to provide customers with as much of this information as possible to enhance their shopping experience. Also it becomes essential to provide same experience for new customers. Our work here focuses on providing a production ready size recommendation system for shoes and address the challenge of providing recommendation for users with no previous purchases on the platform. In our work, we present a probabilistic approach based on user co-purchase data facilitated by generating a brand-brand relationship graph. Specifically we address two challenges that are commonly faced while implementing such solution. 1. Sparse signals for less popular or new products in the system 2. Extending the solution for new users. Further we compare and contrast this approach with our previous work and show significant improvement both in recommendation precision and coverage.