Personalized Ordering of Recommendation-Modules on an E-Commerce Homepage

Abstract

The homepage of an E-Commerce website may accommodate multiple and diverse recommendation modules; with each module is designed to cover some facet of the user’s needs. Commonly, the recommendation modules are ordered in the same way for all homepage users, which leads to a sub-optimal user experience. In this work, we present a novel personalized module ordering solution that provides a more educated way to determine an ordering of the homepage modules based on historical user-interactions. Overall, we evaluate our solution and demonstrate its merits.