TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou
收藏DataCite Commons2025-01-02 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/77a7ec6a-9a95-4ce1-bfd0-3a2f5669f1c8
下载链接
链接失效反馈官方服务：
资源简介：
The dataset is a large-scale industrial dataset collected from Kuaishou, containing user interaction data with click-through as labels. The dataset has a maximum history length of 100,000 items for clustering life-cycle user behavior.
提供机构：
TIB
创建时间：
2025-01-02
