The article discusses the phenomenon of model multiplicity in machine learning, arguing that developers should be legally obligated to search for less discriminatory algorithms (LDAs) to reduce disparities in algorithmic decision-making.
The Digital Benefit Network's Digital Identity Community of Practice held a session to hear considerations from civil rights technologists and human-centered design practitioners on ways to ensure program security while simultaneously promoting equity, enabling accessibility, and minimizing bias.
This report offers a detailed assessment of how AI and emerging technologies could impact the Social Security Administration’s disability benefits determinations, recommending guardrails and principles to protect applicant rights, mitigate bias, and promote fairness.
This academic article develops a framework for evaluating whether and how automated decision-making welfare systems introduce new harms and burdens for claimants, focusing on an example case from Germany.
A comprehensive series of workshops and courses designed to equip public sector professionals with the knowledge and skills to responsibly integrate AI technologies into government operations.​
This reporting explores how algorithms used to screen prospective tenants, including those waiting for public housing, can block renters from housing based on faulty information.
This academic paper examines how federal privacy laws restrict data collection needed for assessing racial disparities, creating a tradeoff between protecting individual privacy and enabling algorithmic fairness in government programs.
ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT)
This UN report warns against the risks of digital welfare systems, emphasizing their potential to undermine human rights through increased surveillance, automation, and privatization of public services.
NIST has created a voluntary AI risk management framework, in partnership with public and private sectors, to promote trustworthy AI development and usage.
National Institute of Standards and Technology (NIST)
This academic paper examines predictive optimization, a category of decision-making algorithms that use machine learning (ML) to predict future outcomes of interest about individuals. Through this examination, the authors explore how predictive optimization can raise concerns that make its use illegitimate and challenge claims about predictive optimization's accuracy, efficiency, and fairness.
This resource helps individuals with aligning their work with the needs of the communities they wish to serve, while reducing the likelihood of harms and risks those communities may face due to the development and deployment of AI technologies.
