Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

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.

Stakeholder-Centered AI Design: Co-Designing Worker Tools with Gig Workers through Data Probes

“…Prior work has explored different approaches for modelling and forecasting passenger travel behavior to predict where passenger demand will occur within certain time intervals [18,55], even using external features such as weather, demographic data, and crime rates [18]. However, these studies focus on demand as the principal element of passenger behavior.…”

Multivariate Transfer Passenger Flow Forecasting with Data Imputation by Joint Deep Learning and Matrix Factorization

“…Except for the aforementioned approaches, ML and its subclass DL have aroused great academic and industrial interest in the past decades [20]. Of these, traditional ML prediction models, such as SVM, RF, XGBoost [21], wavelet transform (WT) [22] and Bayesian networks [23], have achieved favorable forecasting performance in intelligent transportation systems (ITS).…”

Were ride-hailing fares affected by the COVID-19 pandemic? Empirical analyses in Atlanta and Boston

“…Aside from the above-mentioned studies, some researchers have focused their work on forecasting future demand. Time series models (Faghih et al 2019) and machine learning models (Chen et al 2021;Jin et al 2020;Ke et al 2017;Kontou et al 2020;Yan et al 2020) have both been used to predict ride-hailing demand. The operator can make realtime adjustments and assign drivers to riders based on the short-term prediction of ridehailing demand, maximizing service and revenue.…”