GD-ML/CCN

该数据集用于论文《Towards Full Candidate Interaction: A Comprehensive Comparison Network for Better Route Recommendation》的研究，主要任务类别为表格分类。数据集包含三类特征：1) 路由特征（N * 62维），用于描述每条路由的静态特征、动态特征和轨迹统计特征，如预计到达时间和路由总距离；2) 场景特征（1 * 10维），表示路由推荐的上下文信息，如请求时间和用户对起点和终点的熟悉程度；3) 比较级别特征（N * N * 27维），表示两条路由之间非重叠段的属性，如比较差异ETA和比较差异距离。

This dataset is for our paper Towards Full Candidate Interaction: A Comprehensive Comparison Network for Better Route Recommendation, with the task category being tabular-classification. The dataset includes three types of features: 1) Route Features (N * 62 dimensions), used to describe each route, including static features, dynamic features, and trajectory statistical features, such as the estimated time of arrival and the total distance length of the route; 2) Scene Features (1 * 10 dimensions), representing the contextual information of route recommendation, such as request time and user familiarity with the origin and destination; 3) Comparison-Level Features (N * N * 27 dimensions), representing the attributes of the non-overlapping segments between two routes, such as comparison diff eta and comparison diff distance.