Abstract
As ride-hailing services become increasingly popular, being able to accurately predict demand for such services can help operators efficiently allocate drivers to customers, and reduce idle time, improve traffic congestion, and enhance the passenger experience. This paper proposes UberNet, a deep learning convolutional neural network for short-time prediction of demand for ride-hailing services. Exploiting traditional time series approaches for this problem is challenging due to strong surges and declines in pickups, as well as spatial concentrations of demand. This leads to pickup patterns that are unevenly distributed over time and space. UberNet employs a multivariate framework that utilises a number of temporal and spatial features that have been found in the literature to explain demand for ride-hailing services. Specifically, the proposed model includes two sub-networks that aim to encode the source series of various features and decode the predicting series, respectively. To assess the performance and effectiveness of UberNet, we use 9 months of Uber pickup data in 2014 and 28 spatial and temporal features from New York City. We use a number of features suggested by the transport operations and travel behaviour research areas as being relevant to passenger demand prediction, e.g., weather, temporal factors, socioeconomic and demographics characteristics, as well as travel-to-work, built environment and social factors such as crime level, within a multivariate framework, that leads to operational and policy insights for multiple communities: the ride-hailing operator, passengers, third-part location-based service providers and revenue opportunities to drivers, and transport operators such as road traffic authorities, and public transport agencies. By comparing the performance of UberNet with several other approaches, we show that the prediction quality of the model is highly competitive. Further, Ubernet’s prediction performance is better when using economic, social and built environment features. This suggests that Ubernet is more naturally suited to including complex motivators of travel behavior in making real-time demand predictions for ride-hailing services.
Highlights
With the advent of Web 2.0, ride-sharing platforms such as Uber and Lyft are becoming a popular way to travel
This paper proposes UberNet, a deep learning convolutional neural network (CNN) for the short-term demand prediction of ride-hailing services, using spatio-temporal data of Uber pickups in New York City and exogenous features to
We have proposed Ubernet as an approach that can formally utilise the multivariate architecture while being able to utilise the correlations among different features and the long-term dependencies of time series sequences, unlike many other deep learning approaches
Summary
With the advent of Web 2.0, ride-sharing platforms such as Uber and Lyft are becoming a popular way to travel. This paper proposes UberNet, a deep learning convolutional neural network (CNN) for the short-term demand prediction of ride-hailing services, using spatio-temporal data of Uber pickups in New York City and exogenous features to. A core indicator of Uber demand is the so-called unit original pickup (UOP), which is the number of successful Ubertransactions at the platform per unit time (Tong et al 2017). UOP prediction can benefit Uber platform or other ride-hailing services in multiple ways. UOP reflects the willingness of users to complete transactions after adopting new dynamic pricing policies. It can be used to optimize ride-hailing services car allocation. This allows other taxicab platforms to arrange roaming drivers to customers in advance. Predicting UOP accurately is at the core of the online ride-sharing industry
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
