Breaking the Divestment Cycle with Big Data: Predicting Abandonment & Fostering Neighborhood Revitalization

Breaking the Divestment Cycle with Big Data: Predicting Abandonment & Fostering Neighborhood Revitalization

Funded by the 21st Century Cities Initiative and The Institute for Data Intensive Engineering and Science at Johns Hopkins University

In recent years we have witnessed fundamental technological shifts in the way cities collect and leverage data. With the advent of sensor networks and computerized record keeping of public data, research in this area is changing dramatically. A new branch of data-driven science aimed at improving the quality of city life is emerging, and being integrated into redevelopment policy and administration.

We apply this emergent approach to Baltimore’s most visible sign of urban decline: vacant and abandoned housing. After decades of population loss, the city is starting to see revitalization in some areas. Much of this improvement is catalyzed not by traditional heavy-hand urban policy, but by flexible and data driven programs such as Vacants to Value. This project will expand our knowledge of neighborhood change by developing a rich parcel-level longitudinal dataset merging administrative data from Baltimore Housing. We will not only evaluate the efficacy of the city’s programs, but also answer larger questions – examining empirically for the first time the mechanism of property divestment, neighborhood decline, and renewal.