DNEAT: A novel dynamic node-edge attention network for origin-destination demand prediction

The ride-hailing service platforms have grown tremendously around the world and attracted a wide range of research interests. A key to ride-hailing service platforms is how to realize accurate and reliable demand prediction. However, most of the existing studies focus on the region-level demand prediction while only a few attempts to address the problem of origin-destination (OD) demand prediction. In this paper, from the graph aspects, we construct the dynamic OD graphs to describe the ride-hailing demand data. We propose a novel neural architecture named the Dynamic Node-Edge Attention Network (DNEAT) to address the unique challenges of OD demand prediction from the demand generation and attraction perspectives. Different from previous studies, in DNEAT, we develop a new neural layer, named k-hop temporal node-edge attention layer (K-TNEAT), to capture the temporal evolution of node topologies in dynamic OD graphs instead of the pre-defined relationships among regions. We evaluate our model on two real-world ride-hailing demand datasets (from Chengdu, China, and New York City). The experiment results show that the proposed model outperforms six baseline models and is more robust to demand data with high sparsity.