Saved in:
Bibliographic Details
Main Authors: Anghinoni, Leandro, Zivic, Pablo, Sanchez, Jorge Adrian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908403886981120
author Anghinoni, Leandro
Zivic, Pablo
Sanchez, Jorge Adrian
author_facet Anghinoni, Leandro
Zivic, Pablo
Sanchez, Jorge Adrian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revisiting Graph Projections for Effective Complementary Product Recommendation
Anghinoni, Leandro
Zivic, Pablo
Sanchez, Jorge Adrian
Information Retrieval
Machine Learning
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.
title Revisiting Graph Projections for Effective Complementary Product Recommendation
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2506.09209