WindyStu/data_sample_1000

这是一个用于TAAC2026竞赛的演示数据集，包含1000条用户-物品交互记录。数据集采用扁平列布局，所有特征都作为顶级列存储。数据集包含120列，分为6个类别：ID和标签、用户整数特征、用户密集特征、物品整数特征和领域序列特征。ID和标签列包括用户ID、物品ID、标签类型、标签时间和时间戳。用户整数特征包括35个标量列和11个数组列。用户密集特征包括10个浮点数组列。物品整数特征包括13个标量列和1个数组列。领域序列特征包括来自4个行为领域的45个序列列。

A sample dataset containing 1000 user-item interaction records for the TAAC2026 competition. This dataset uses a flat column layout — all features are stored as individual top-level columns instead of nested structs/arrays. The dataset contains 120 columns, divided into 6 categories: ID & Label, User Int Features, User Dense Features, Item Int Features, and Domain Sequence Features. The ID & Label columns include user_id, item_id, label_type, label_time, and timestamp. User Int Features include 35 scalar columns and 11 array columns. User Dense Features include 10 float array columns. Item Int Features include 13 scalar columns and 1 array column. Domain Sequence Features include 45 sequence columns from 4 behavioral domains.