{"ID":2884017,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.14059","arxiv_id":"2508.14059","title":"Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph","abstract":"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.","short_abstract":"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 architectur...","url_abs":"https://arxiv.org/abs/2508.14059","url_pdf":"https://arxiv.org/pdf/2508.14059v1","authors":"[\"Mengyang Cao\",\"Frank F. Yang\",\"Yi Jin\",\"Yijun Yan\"]","published":"2025-08-10T02:12:04Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}