Learning to Rank Paths in Spatial Networks

Modern navigation services often provide multiple paths connecting the same source and destination for users to select. Hence, ranking such paths becomes increasingly important, which directly affects service quality. We present PathRank, a data-driven framework for ranking paths based on historical trajectories. If a trajectory used path P from source s to destination d, PathRank considers this as an evidence that P is preferred over all other paths from s to d. Thus, a path that is similar to P should have a larger ranking score than a path that is dissimilar to P. Based on this intuition, PathRank models path ranking as a regression problem that assigns each path a ranking score. We first propose an effective method to generate a compact set of diversified paths using trajectories as training data. Next, we propose an end-to-end deep learning framework to solve the regression problem. In particular, a spatial network embedding is proposed to embed each vertex to a feature vector by considering the road network topology. Since a path is represented by a sequence of vertices, which is now a sequence of feature vectors after embedding, recurrent neural network is applied to model the sequence. Empirical studies on a substantial trajectory data set offer insight into the designed properties of the proposed framework and indicating that it is effective and practical.