A Multimodal Recommender System for Large-scale Assortment Generation in E-commerce
This addresses the challenge of generating large-scale, style-coherent product assortments for e-commerce platforms like Overstock, particularly for furniture categories, though it is incremental as it builds on existing multimodal and topic modeling approaches.
The paper tackled the problem of automatically curating complementary furniture assortments in e-commerce by proposing two visually-aware recommender systems, one using visual data and another incorporating both visual and textual data, with results showing that incorporating both modalities best discovers style compatibility.
E-commerce platforms surface interesting products largely through product recommendations that capture users' styles and aesthetic preferences. Curating recommendations as a complete complementary set, or assortment, is critical for a successful e-commerce experience, especially for product categories such as furniture, where items are selected together with the overall theme, style or ambiance of a space in mind. In this paper, we propose two visually-aware recommender systems that can automatically curate an assortment of living room furniture around a couple of pre-selected seed pieces for the room. The first system aims to maximize the visual-based style compatibility of the entire selection by making use of transfer learning and topic modeling. The second system extends the first by incorporating text data and applying polylingual topic modeling to infer style over both modalities. We review the production pipeline for surfacing these visually-aware recommender systems and compare them through offline validations and large-scale online A/B tests on Overstock. Our experimental results show that complimentary style is best discovered over product sets when both visual and textual data are incorporated.