Complementary Recommendation in E-commerce: Definition, Approaches, and Future Directions
Linyue Li, Zhijuan Du
TL;DR
This survey addresses the shift from traditional similarity-based recommendations to complementary product suggestions in e-commerce. It outlines a two-tier modeling framework, distinguishing simple versus complex complementary relationships learned from content, purchase sequences, and graphs, and it highlights asymmetry, higher-order dependencies, and multi-relational signals. The paper catalogues 34 studies (2009–2024), contrasting models on diversity, personalization, scenario adaptation, cold-start handling, interpretability, and data noise, and it synthesizes commonly used datasets, losses, optimizers, and evaluation metrics. It also maps out future directions, including semantic and usage-based modeling, sequential and generative retrieval paradigms, and multimodal data handling, aiming to advance practical, scalable, and explainable complementary recommendation systems.
Abstract
In recent years, complementary recommendation has received extensive attention in the e-commerce domain. In this paper, we comprehensively summarize and compare 34 representative studies conducted between 2009 and 2024. Firstly, we compare the data and methods used for modeling complementary relationships between products, including simple complementarity and more complex scenarios such as asymmetric complementarity, the coexistence of substitution and complementarity relationships between products, and varying degrees of complementarity between different pairs of products. Next, we classify and compare the models based on the research problems of complementary recommendation, such as diversity, personalization, and cold-start. Furthermore, we provide a comparative analysis of experimental results from different studies conducted on the same dataset, which helps identify the strengths and weaknesses of the research. Compared to previous surveys, this paper provides a more updated and comprehensive summary of the research, discusses future research directions, and contributes to the advancement of this field.