t-tech/T-ECD

T-ECD（T-Tech电子商务跨域数据集）是一个用于推荐系统研究的大型合成跨域数据集，由T-Bank的推荐系统研发团队创建。它通过合成的方式捕捉了现实世界电子商务跨多个领域的用户交互模式，并保证了用户和品牌的完全匿名。数据集分为两个版本：T-ECD Small（包含约1B交互）和T-ECD Full（包含约135B交互）。数据集覆盖了市场、零售、支付、优惠和评论五个不同的电子商务领域。

T-ECD (T-Tech E-commerce Cross-Domain Dataset) is a large-scale synthetic cross-domain dataset for recommender systems research, created by T-Banks RecSys R&D team. It captures real-world e-commerce interaction patterns across multiple domains while ensuring complete anonymity through synthetic generation. The dataset is available in two versions: T-ECD Small (with approximately 1B interactions) and T-ECD Full (with approximately 135B interactions). It covers five different e-commerce domains: Marketplace, Retail, Payments, Offers, and Reviews.