Amazon Book Data Set

该数据集包含了从亚马逊获取的书籍评论和元数据，这些数据被转换成了一个点击率预测的数据集。数据集的特征字段包括用户ID、历史（点击过）的物品ID、历史（点击过）的物品类别、物品ID以及物品类别。该数据集的规模为150,016个样本，包含425,970个独特的ID。其任务是进行点击率预测。

This dataset comprises book reviews and metadata obtained from Amazon, and has been transformed into a click-through rate (CTR) prediction dataset. Its feature fields include user ID, historical clicked item IDs, historical clicked item categories, item ID, and item category. The dataset contains 150,016 samples and 425,970 unique IDs, with the core task being click-through rate prediction.