Data-Driven Approaches to Identifying and Addressing Housing Inequality and Disaster Vulnerability in U.S: A Critical Review

Housing inequality and disaster vulnerability remain pressing and interconnected challenges in the United States, disproportionately affecting historically marginalized populations. Communities facing inadequate housing, economic precarity, and spatial segregation often bear the brunt of climate-induced disasters such as floods, wildfires, and hurricanes. These overlapping vulnerabilities not only exacerbate social inequities but also hinder effective emergency response and long-term recovery. This review critically examines the role of data-driven approaches in identifying and addressing these dual crises. The paper synthesizes a wide range of methodologies, such as Geographic Information Systems (GIS), remote sensing, social vulnerability indices, machine learning models, and participatory data tools that are increasingly used to assess housing conditions, map hazard exposure, and support targeted interventions. Emphasis is placed on the integration of demographic, infrastructural, and environmental datasets to uncover spatial patterns of risk and inequity. Key findings highlight both the promise and limitations of current data-driven practices. While these tools enhance risk assessment, support predictive modeling, and inform equitable policy design, they are often constrained by data silos, methodological bias, and limited representation of community knowledge. The review highlights the importance of ethical data governance, transparency, and inclusive data collection in advancing socially just outcomes. The paper concludes with policy recommendations that call for enhanced interagency collaboration, investments in local data capacity, and the development of standardized frameworks to align housing and disaster resilience planning. Together, these strategies can help build more adaptive, equitable, and data-informed urban futures.