We consider an on-demand service platform using earning-sensitive independent providers with heterogeneous reservation price (for work participation) to serve its time and price-sensitive customers with heterogeneous valuation of the service. As such, the supply and demand are “endogenously” dependent on the price the platform charges its customers and the wage the platform pays its independent providers. We present an analytical model with endogenous supply (number of participating agents) and endogenous demand (customer request rate) to study this on-demand service platform. To coordinate endogenous demand with endogenous supply, we include the steady-state waiting time performance based on a queueing model in the customer utility function to characterize the optimal price and wage rates that maximize the profit of the platform. We first analyze a base model that uses a fixed payout ratio (i.e., the ratio of wage over price), and then extend our model to allow the platform to adopt a time-based payout ratio. We find that it is optimal for the platform to charge a higher price when demand increases; however, the optimal price is not necessarily monotonic when the provider capacity or the waiting cost increases. Furthermore, the platform should offer a higher payout ratio as demand increases, capacity decreases or customers become more sensitive to waiting time. We also find that the platform should lower its payout ratio as it grows with the number of providers and customer demand increasing at about the same rate. We use a set of actual data from a large on-demand ride-hailing platform to calibrate our model parameters in numerical experiments to illustrate some of our main insights.

Regulating on-demand ride-hailing services (e.g., Uber and DiDi) requires a balance of multiple competing objectives: encouraging innovative business models (e.g., DiDi), sustaining traditional industries (e.g., taxi), creating new jobs, and reducing traffic congestion. This study is motivated by a regulatory policy implemented by the Chinese government in 2017 and a similar policy approved by the New York City Council in 2018 that regulate the “maximum” number of registered Uber/DiDi drivers. We examine the impact of these policies on the welfare of different stakeholders (i.e., consumers, taxi drivers, on-demand ride service company, and independent drivers). By analyzing a two-period dynamic game that involves these stakeholders, we find that, without government intervention, the on-demand ride service platform can drive the traditional taxi industry out of the market under certain conditions. Relative to no regulations and a complete ban policy, a carefully designed regulatory policy can strike a better balance of multiple competing objectives. Finally, if a government can reform the taxi industry by adjusting the taxi fare, then lowering the taxi fare instead of imposing a strict policy toward on-demand ride services can improve the total social welfare. This paper was accepted by Serguei Netessine, operations management.

Ride-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy. To capture the spatio-temporal characteristics in a hexagonal manner, we propose three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps. Moreover, a hexagon-based ensemble mechanism is developed to enhance the prediction performance. Validated by a 3-week real-world ride-sourcing dataset in Guangzhou, China, the H-CNN models are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness. Our approaches can be further extended to a broad range of spatio-temporal forecasting problems in the domain of shared mobility and urban computing.

This study provides a comprehensive review of the significant elements in sustainable transportation systems with shared mobility. The main subsets of shared mobility includes ridesharing, carsharing, shared micromobility, on-demand ride services, and shared autonomous vehicles (SAVs). This paper revisits the related studies in the last decade since shared mobility spread via the emergence of smartphones and numerous applications. A framework is proposed to describe the shared mobility systems and understand the interactions among various elements in shared mobility systems, such as the supply and demand relationship between users and enterprises. Based on this framework, many fundamental research problems of shared mobility systems are summarized to cover travel behavior, enterprise supply, government policy, and sustainability. With the sustainability theme of shared mobility, we review the literature on the impacts of shared mobility on transportation sustainability. It is discovered that shared mobility has many advantages and improves urban transportation systems in many aspects, but these benefits vary with travel behavior and enterprise supply. We also discuss how government policies regulate travel behavior and enterprise supply in the sustainable development of urban transportation systems.