baimaozi/data_sample_1000

这是一个包含1000条用户-物品交互记录的样本数据集，专为TAAC2026竞赛设计。数据集采用扁平列布局，所有特征都作为独立的顶级列存储，而非嵌套结构或数组。数据集包含120列，分为6个类别：ID与标签（5列）、用户整数特征（46列）、用户密集特征（10列）、物品整数特征（14列）和领域序列特征（45列）。这些特征涵盖了用户和物品的多种属性，以及来自4个行为领域的序列数据，用于推荐系统任务。

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. It includes 120 columns categorized into 6 groups: ID & Label (5 columns), User Int Features (46 columns), User Dense Features (10 columns), Item Int Features (14 columns), and Domain Sequence Features (45 columns). These features cover various user and item attributes, as well as sequence data from 4 behavioral domains, for recommendation system tasks.