Predicting Short-Term Uber Demand in New York City Using Spatiotemporal Modeling

Abstract

The demand for e-hailing services is growing rapidly, especially in large cities. Uber is the first and most popular e-hailing company in the United States and New York City (NYC). A comparison of the demand for yellow cabs and Uber in NYC in 2014 and 2015 shows that the demand for Uber has increased. However, this demand may not be distributed uniformly either spatially or temporally. Using spatiotemporal models can help us to better understand the demand for e-hailing services and to predict it more accurately. This paper proposes a new approach for analyzing and predicting the Uber demand. Moreover, the prediction performances of several statistical models are compared including one temporal model [vector autoregressive (VAR)] and two proposed spatiotemporal models [spatial-temporal autoregressive (STAR) and least absolute shrinkage and selection operator applied on STAR (LASSO-STAR)], for different scenarios (based on the number of time and space lags), and for both rush hour and non-rush hour periods. The results show the need of considering spatial models for taxi demand and demonstrate significant improvement in the prediction of demand using the two proposed models.