Sarah Bardin is a leader in applied data science and policy research, specializing in spatial analytics, quantitative methods, and the use of artificial intelligence to strengthen program evaluation and policy design. Her work focuses on federal nutrition assistance and human services programs, with an emphasis on how place-based factors shape access, implementation, and outcomes.
Bardin brings deep experience designing and directing large-scale quantitative research and evaluation projects for federal and foundation clients. She currently serves as analytic lead for the National School Food Study, the largest evaluation of the National School Lunch Program and School Breakfast Program in U.S. history. She is also principal investigator for a multi-year study examining participant access to WIC-authorized vendors for the U.S. Department of Agriculture. Her recent work includes directing studies assessing alternative approaches for determining maximum Supplemental Nutrition Assistance Program (SNAP) benefits and evaluating the convenience and variety of Thrifty Food Plan market baskets. Across her portfolio, Bardin integrates administrative, survey, and community-level data with advanced analytic approaches to generate actionable insights for clients on what works, where, and for whom.
As Director of Innovation, Bardin leads efforts to embed new analytic approaches and technologies into project work across the division. She works closely with subject matter experts and data scientists to identify high-value opportunities for innovation, pilot and scale new methods, and translate emerging capabilities into practical applications for client work. She provides AI consultation and implementation support to teams and integrates generative AI into research workflows to improve the scalability, quality, and efficiency of working with large volumes of unstructured data. Her work includes developing AI-enabled approaches to support literature and document review, building repeatable workflows for thematic analysis, and extracting and structuring data from diverse unstructured sources—including images, websites, and hard-copy data collection forms—into analysis-ready formats.
Bardin holds a PhD in Geography from Arizona State University and a BA in Public Policy Studies and Political Science from the University of Chicago.
To solve their most pressing challenges, organizations turn to Mathematica for deeply integrated expertise. We bring together subject matter and policy experts, data scientists, methodologists, and technologists who work across topics and sectors to help our partners design, improve, and scale evidence-based solutions.
Work With Us