Reparative Urban Science: Challenging the Myth of Neutrality and Crafting Data-Driven Narratives

Abstract

This dissertation constructs a distinctive lens on how we should see urban technology in the context of a long history of systemic racism, and how we can take a reparative approach to intervene in contemporary situations of racial inequality with technology/data as a method to address systemic racism. The current discourse of urban science often puts an emphasis on newly available (and big) data, primarily values methodologies of “hard” sciences such as physics, computer science, and mathematics, and evolves to incorporate the latest technologies and analytic methods including machine learning and artificial intelligence. However, the role of urban science and analytics that “move[s] beyond analysis” has not been extensively theorized. In particular, the relationship between urban technologies, white supremacy, and racial capitalism has not been extensively studied. Nonetheless, the impact of the applications of such “urban analysis” on people’s lives has been substantial. Building on planning scholars’ calls for reparative planning and emerging discourses of “algorithmic reparation,” this dissertation proposes a normative framework of reparative urban science that challenges whiteness in urban science and embraces the epistemologies and methodologies of reparations.

The dissertation follows a three-paper structure, with the first paper serving as the theoretical framework for two empirical studies, and includes a concluding chapter. The first paper introduces the overarching theory of reparative urban science, identifying three mechanisms—formalizing, context removal and legitimization, and penalization—through which urban technologies perpetuate historical inequalities under a race-neutral guise. It then proposes reparative methodologies, including algorithmic auditing, crowd-sourced community data collection, and algorithms designed to simulate and deliberate reparative futures. The second and third papers demonstrate reparative urban science in action, exemplifying these methodologies. The second paper investigates tenant screening services and landlord decision-making. It reveals the mechanisms how tenant screening algorithms contribute to obscuring historical racial biases, and how landlords interact with them to exert harms. The third paper evaluates the reparative potential of housing programs using algorithmic methods, particularly comparing race-neutral versus race-conscious Special Purpose Credit Programs (SPCPs). It demonstrates that race-conscious SPCPs could significantly reduce the racial housing wealth gap than race-neutral ones, showing race-conscious policies as potential reparative tools. The concluding chapter explores theoretical and practical considerations of housing reparations through the lens of reparative justice, arguing for a deeper acknowledgment of the historical and structural harms related to land and property. Overall, this dissertation seeks to reorient urban science toward justice and repair, envisioning a transformative path forward that actively confronts historical harms and promotes healing and equity in urban futures.