Predicting Destinations by a Deep Learning based Approach

Destination prediction is known as an important problem for many location based services (LBSs). Existing solutions generally apply probabilistic models or neural network models to predict destinations over a subtrajectory, and adopt the standard attention mechanism to improve the prediction accuracy. However, the standard attention mechanism uses fixed feature representations, and has a limited ability to represent distinct features of locations. Besides, existing methods rarely take the impact of spatial and temporal characteristics of the trajectory into account. Their accuracies in fine-granularity prediction are always not satisfactory due to the data sparsity problem. Thus, in this paper, a carefully designed deep learning model called LATL model is presented. It not only adopts an adaptive attention network to model the distinct features of locations, but also implements time gates and distance gates into the Long Short-Term Memory (LSTM) network to capture the spatial-temporal relation between consecutive locations. Furthermore, to better understand the mobility patterns in different spatial granularities, and explore the fusion of multi-granularity learning capability, a hierarchical model that utilizes tailored combination of different neural networks under multiple spatial granularities is further proposed. Extensive empirical studies verify that the newly proposed models perform effectively and settle the problem nicely.

Automated summary

A newly proposed deep learning model called LATL adopts an adaptive attention network to model distinct features of locations and implements time gates and distance gates into the LSTM network to capture spatial-temporal relations. Furthermore, a hierarchical model that utilizes tailored combination of different neural networks under multiple spatial granularities is proposed to better understand mobility patterns and explore multi-granularity learning capability. Extensive empirical studies verify the effectiveness of the newly proposed models in solving the destination prediction problem.