Amazon product co-purchasing network and ground-truth communities

Yang, Jaewon; Leskovec, Jure

2012

This dataset provides a comprehensive view of product relationships on Amazon, based on the "Customers Who Bought This Item Also Bought" feature. Products are represented as nodes, and an undirected edge between two products signifies frequent co-purchasing, reflecting consumer buying patterns and product associations. ​If a product i is frequently co-purchased with product j, the graph contains an undirected edge from i to j. Each product category provided by Amazon defines each ground-truth community. We regard each connected component in a product category as a separate ground-truth community. We remove the ground-truth communities which have less than 3 nodes. We also provide the top 5,000 communities with highest quality which are described in our paper. The dataset has a size of 0,01 GB and encompasses 334,863 nodes (products) and 925,872 edges (co-purchasing relationships).

The dataset is structured into:​

• Network Data: An undirected graph where nodes represent products, and edges indicate co-purchasing relationships.​

• Ground-Truth Communities: Each product category defined by Amazon serves as a ground-truth community. Connected components within these categories are treated as separate communities, excluding those with fewer than three nodes. Additionally, the dataset provides the top 5,000 communities with the highest quality, as detailed in the associated research paper.