The University of Massachusetts Amherst


Ride sourcing, or the use of private cars to provide on-demand transportation services, has recently been in the news as the most disruptive mode of transport related to the so-called “shared mobility era.” Now Principal Investigator Song Gao of the Civil and Environmental Engineering (CEE) Department has received a three-year, $495,638 grant from the National Science Foundation (NSF) to investigate pioneering behavioral insights and algorithmic tools for improving the efficiency of ride-sourcing drivers.

The title of Gao’s NSF project is "Understanding and optimizing Ride-sourcing drivers’ lEArning DYnamics (or READY).”

According to Gao, her READY project will work with drivers to obtain location and operational data and generate optimized guidance on how to maximize their welfare. Gao believes her work could enable transportation agencies and local communities to partner with ride-sourcing drivers to gain insights into the market and enhance policies to meet general societal goals.

“The independence of ride-sourcing drivers comes at the price of social isolation and anxiety,” says Gao. “This project will chart a technology inspired pathway to better connection and organization of the diffusive workforce and increase its cohesion, vitality, and social contribution.”

Gao adds that “Ride-sourcing drivers are more likely from the lower income and other vulnerable parts of the population, and the project prototype serves as an outreach tool to improve their well-being, in addition to being a test bed for [my] research program.”

Gao explains that there are three major research objectives in her NSF project. One is to understand the learning and choice behaviors of ride-sourcing drivers by using dynamic discrete choice models grounded on psychologically sound learning theories.

A second objective is to develop model-based and model-free algorithms to optimize decisions by ride-sourcing drivers on such issues as when they should start and end working, where they should search for passengers, and whether or not it’s advantageous for them to accept particular ride requests.

Finally, her NSF project will “generate behaviorally informed driver guidance synthesizing results from the previous two objectives.”

Gao’s NSF research has several groundbreaking aspects, including the fact that it provides an alternative approach to enhancing the ride-sourcing market by directly working with drivers instead of the more impersonal platforms commonly used in the scientific literature and practice. Gao also says that her driver-centered approach is far more fair and more socially efficient due to its collaborative nature.

Gao concludes that her integrated approach will fill a key knowledge gap by finally explaining the low retention rates of ride-sourcing drivers and will contribute to the development of high-performance optimization algorithms for ride-sourcing operations.

Gao’s research lab in the CEE department is focused on experimental studies and econometric models of choice behavior in transportation networks, optimization algorithms in stochastic networks, and network equilibrium models in uncertain systems with real-time information. (June 2023)

Article posted in Research