Housing abandonment in urban American communities presents a profound challenge for residents and city governments. In Kansas City, over 10,000 houses have been abandoned, with safe demolition costing $10,000 per house. However, demolition further weakens the physical and social fabric of disadvantaged neighborhoods. This proposal empowers community members, city leaders, technologists, and local public-school students in a planning process to leverage the use of Artificial Intelligence (AI). The proposal leverages collaboration with the municipal government to use cameras on city vehicles to identify early markers of housing decay. The intention is to develop an early warning system where local government and neighborhood associations can provide micro-policy inputs in order to halt the process of abandonment.

This project has formed a well-integrated multidisciplinary team of data scientists, community leaders and social scientists to lay out the scientific and engineering foundations for addressing the issue of abandoned housing. In this planning grant, the project concentrate on a small neighborhood of Kansas City, Missouri (KCMO) to develop the tools and planning required for reducing the issue of housing abandonment. Specifically, the project will focus on the Ivanhoe neighborhood, which is home to around 5,500 mostly low-income minority residents (95% African-American, 35% below the poverty level) and which has about 40% of its land occupied by vacant lots and abandoned properties. Specific objectives of this project are i) enhancing scientific knowledge of housing abandonment by applying deep learning technology and statistical modeling, ii) fostering a multidisciplinary and diverse research community to develop tools for measuring, predicting, and preventing the spread of housing abandonment, and iii) integrating KCMO’s community stakeholders into a series of community projects for optimal self-control to reduce abandoned housing and resolve residual problems.