DeepETA: A Spatial-Temporal Sequential Neural Network Model for Estimating Time of Arrival in Package Delivery System
Over 100 million packages are delivered every day in China due to the fast development of e-commerce. Precisely estimating the time of packages’ arrival (ETA) is significantly important to improving customers’ experience and raising the efficiency of package dispatching. Existing methods mainly focus on predicting the time from an origin to a destination. However, in package delivery problem, one trip contains multiple destinations and the delivery time of all destinations should be predicted at any time. Furthermore, the ETA is affected by many factors especially the sequence of the latest route, the regularity of the delivery pattern and the sequence of packages to be delivered, which are difficult to learn by traditional models. This paper proposed a novel spatial-temporal sequential neural network model (DeepETA) to take fully advantages of the above factors. DeepETA is an end-to-end network that mainly consists of three parts. First, the spatial encoding and the recurrent cells are proposed to capture the spatial-temporal and sequential features of the latest delivery route. Then, two attention-based layers are designed to indicate the most possible ETA from historical frequent and relative delivery routes based on the similarity of the latest route and the future destinations. Finally, a fully connected layer is utilized to jointly learn the delivery time. Experiments on real logistics dataset demonstrate that the proposed approach has outperforming results.