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.
View on arXiv@article{anghinoni2025_2506.09209, title={ Revisiting Graph Projections for Effective Complementary Product Recommendation }, author={ Leandro Anghinoni and Pablo Zivic and Jorge Adrian Sanchez }, journal={arXiv preprint arXiv:2506.09209}, year={ 2025 } }