Revisiting Graph Projections for Effective Complementary Product Recommendation
This addresses the challenge of noisy and sparse interactions in retail to enhance customer experience and sales, representing a strong specific gain in the domain.
The paper tackled the problem of complementary product recommendation by proposing a method based on directed weighted graph projections from user-item interactions, resulting in average improvements of +43% over sequential and +38% over graph-based recommenders across benchmarks.
Complementary product recommendation is a powerful strategy to improve customer experience and retail sales. However, recommending the right product is not a simple task because of the noisy and sparse nature of user-item interactions. In this work, we propose a simple yet effective method to predict a list of complementary products given a query item, based on the structure of a directed weighted graph projected from the user-item bipartite graph. We revisit bipartite graph projections for recommender systems and propose a novel approach for inferring complementarity relationships from historical user-item interactions. We compare our model with recent methods from the literature and show, despite the simplicity of our approach, an average improvement of +43% and +38% over sequential and graph-based recommenders, respectively, over different benchmarks.