Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
By: Mengyang Cao , Frank F. Yang , Yi Jin and more
Potential Business Impact:
Helps online stores show you better stuff.
Identifying relevant information among massive volumes of data is a challenge for modern recommendation systems. Graph Neural Networks (GNNs) have demonstrated significant potential by utilizing structural and semantic relationships through graph-based learning. This study assessed the abilities of four GNN architectures, LightGCN, GraphSAGE, GAT, and PinSAGE, on the Amazon Product Co-purchase Network under link prediction settings. We examined practical trade-offs between architectures, model performance, scalability, training complexity and generalization. The outcomes demonstrated each model's performance characteristics for deploying GNN in real-world recommendation scenarios.
Similar Papers
Building a Recommendation System Using Amazon Product Co-Purchasing Network
Social and Information Networks
Suggests new items customers will like.
Benchmarking Deep Neural Networks for Modern Recommendation Systems
Information Retrieval
Finds best movies and products for you.
On the Impact of Graph Neural Networks in Recommender Systems: A Topological Perspective
Information Retrieval
Helps computers pick better movies and songs.