SCASRec
收藏资源简介:
该数据集用于论文《SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List Recommendation》中的研究,属于表格分类任务。数据集包含三种特征类型:路线特征、场景特征和长期特征。路线特征用于描述每条路线的静态、动态和轨迹统计特征,维度为N*62,关键特征包括路线的预计到达时间和总距离长度。场景特征表示路线推荐的上下文信息,维度为1*10,关键特征包括请求时间以及用户对起点和终点的熟悉程度。长期特征是一系列按时间顺序排列的路线选择记录,维度为T*31,关键特征包括已选和未选路线的特征。该数据集适用于生成式路线列表推荐任务。
This dataset is employed in the study presented in the paper "SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List Recommendation", and falls under the table classification task. The dataset encompasses three categories of features: route features, scenario features, and long-term features. Route features describe the static, dynamic and trajectory statistical characteristics of each route, with a dimensionality of N×62. Its key features include the estimated time of arrival and total route distance. Scenario features represent the contextual information for route recommendation, with a dimensionality of 1×10. Its key features include the request time and the user's familiarity with the origin and destination locations. Long-term features consist of a series of chronologically ordered route selection records, with a dimensionality of T×31. Its key features include the features of both selected and unselected routes. This dataset is applicable to generative route list recommendation tasks.




