Matching Rider Demand and Sharing Service in Transportation Infrastructure Networks for the Pittsburgh Metropolitan Area

The research addresses inefficiencies in ride-sharing services by developing predictive models for traveler demand. Sharing services are not provided optimally — passengers struggle to find vehicles at reasonable prices while drivers miss revenue opportunities due to incomplete demand knowledge.

Working with Gridwise, a Pittsburgh-based startup, the team aimed to create models using multiple data sources including the CMU Mobility Data Analytics Center and Gridwise platform data. The initiative focused on improving three outcomes: better service accessibility for travelers, enhanced revenue prospects for drivers, and strengthened overall transportation infrastructure performance.

The underlying motivation reflects broader transportation challenges: the 256 million private vehicles in the U.S. impose substantial costs and generate significant congestion. Ride-sharing systems offer potential environmental and economic benefits through reduced vehicle ownership needs and improved traffic-flow efficiency.