Predicting passenger origin-destination in online taxi-hailing systems

Because of transportation planning, traffic management, and dispatch optimization importance, passenger origin-destination prediction has become one of the most important requirements for intelligent transportation systems management. In this paper, we propose a model to predict the next specified time window travels' origin and destination. To extract meaningful travel flows, we use K-means clustering in four-dimensional space with maximum cluster size limitation for origin and destination zones. Because of the large number of clusters, we use non-negative matrix factorization to decrease the number of travel clusters. Also, we use a stacked recurrent neural network model to predict travel count in each cluster. Comparing our results with other existing models show that our proposed model has 5-7% lower mean absolute percentage error (MAPE) for 1-hour time windows, and 14% lower MAPE for 30-minute time windows.