Erica Baird

Milliman

PHD, FSA, MAAA
Principal & Consulting Actuary

Erica is a principal and consulting actuary with the Minneapolis office of Milliman. She joined the firm in 2013. 

Erica has extensive experience designing and calibrating predictive models, and she is involved in ongoing research and development of the models included in the Milliman Advanced Risk Adjusters (MARA) software. She has also developed custom predictive models for application in unique circumstances, and has worked with models in the context of commercial, Medicare, and Medicaid populations.

In addition to predictive modeling, Erica also has experience evaluating outcomes for payers and providers for the purposes of trend guarantees or shared savings arrangements. She also has experience pricing and filing premium rates for group health insurance plans subject to the Affordable Care Act’s healthcare reforms and in developing bids for Medicare Advantage and Part D plans.

Prior to joining the firm, Erica taught mathematics while pursuing her PhD.

Presentation: The intersection between health equity and risk adjustment in Medicaid

Abstract: Persistent health disparities have prompted increased attention to health equity among federal and state policymakers. State Medicaid agencies, as major purchasers of care for diverse and often underserved populations, are uniquely positioned to influence equity through financing and policy decisions. To support these efforts, we examined how clinical, demographic, geographic, and social factors—including race and ethnicity—are associated with patterns of healthcare utilization in Medicaid populations.

A central challenge in this work is the incomplete and inconsistent collection of race and ethnicity data, which constrains the measurement and interpretation of inequities. Prior to this analysis, and through research sponsored by the Society of Actuaries Research Institute, we conducted a separate line of research evaluating racial and ethnic imputation methods currently in use, including Bayesian Improved Surname Geocoding (BISG), with a case study using Medicaid data. This earlier work provided an important perspective on the strengths, limitations, and appropriate applications of imputation algorithms in actuarial research.

Together, these complementary research streams highlight the interplay between methodological choices and equity analysis. This presentation reflects on how advances in data and modeling—when applied thoughtfully—can help actuaries and policymakers better understand disparities, while underscoring the limitations and challenges associated with the use of imputed race and ethnicity data in equity‑focused decision‑making.

Daniel Bauer

Wisconsin School of Business, University of Wisconsin–Madison

Professor of Risk and Insurance and Hickman-Larson Distinguished Chair in Actuarial Science  
Senior Associate Dean for Programs 

Dani Bauer is the Senior Associate Dean for Programs at the Wisconsin School of Business and the Hickman-Larson Distinguished Chair in Actuarial Science in the Department of Risk and Insurance.

Dani’s research appears in leading journals in actuarial science, economics, finance, management, and statistics. He has been recognized with several research and teaching awards. Dani has served as co-editor and in other senior editorial roles at leading journals in actuarial science and risk management. He has taught classes in actuarial science, quantitative finance, risk management, data analytics, and machine learning, and has mentored doctoral students who have gone on to faculty positions at leading universities. In his current role as Senior Associate Dean for Programs, Dani oversees the entire program portfolio of the Wisconsin School of Business and the teams managing the undergraduate and graduate programs. Before stepping into the dean’s office, he chaired the Department of Risk and Insurance. He has served as an adviser and expert on insurance and insurance-linked investments for government agencies and industry.

Dani earned his MS in Statistics from San Diego State University and his PhD in Mathematics from Ulm University. Prior to joining the faculty at UW-Madison, Dani was the Dai-ichi Life Insurance Company Endowed Chair in Actuarial Science and Risk Management at Culverhouse College of Commerce at the University of Alabama and Robert W. Batten Chair in Actuarial Science at the J. Mack Robinson College of Business at Georgia State University.

Presentation: What Is a Life Worth? Multi-State Actuarial Models for Valuing Health and Longevity

Abstract: The Value of Statistical Life (VSL) is one of the most consequential numbers in public policy, shaping investments in medical research, environmental protection, and pandemic preparedness, and underlying cost-effectiveness thresholds in health systems around the world. Yet VSL is largely absent from actuarial training and research — even though the models economists use to derive it are close cousins of the models actuaries build every day.

In this talk, I will introduce VSL and its generalization, the Value of Statistical Illness (VSI), and show how actuarial tools — continuous-time multi-state models, life contingent valuation, and life-cycle optimization under incomplete markets — can be combined to produce novel frameworks for valuing health and longevity. I will illustrate with recent results explaining why people pay more per quality-adjusted life-year when sick, and why conventional valuations of medical advances can substantially overstate aggregate welfare gains.

Fei Huang

School of Risk and Actuarial Studies, UNSW Business School

Associate Professor of Risk and Actuarial Studies

Dr. Fei Huang is an Associate Professor of Risk and Actuarial Studies at UNSW Business School. Her research lies at the intersection of responsible AI, insurance, and data-driven decision-making, with a focus on ensuring that insurance and retirement income systems remain fair, sustainable, and resilient to climate risk and technological change. Drawing on statistics, machine learning, economics, and actuarial science, she develops insurance solutions that are accurate, interpretable, and equitable. Her work has received multiple academic and professional awards and is supported by major competitive funding. Fei works closely with industry and regulators on responsible AI in insurance. Her work bridges research, policy, and practice, shaping regulatory thinking and supporting the responsible use of data-driven decision systems. For more information, please visit www.feihuang.org. 

Presentation: Responsible AI and Data Science for Fair Insurance Pricing

Abstract: Advances in AI and data science are transforming insurance pricing, enabling increasingly granular risk assessment and improved predictive accuracy. However, these developments also raise fundamental challenges for fairness, transparency, and accountability. Insurance pricing models may inadvertently embed indirect discrimination through complex data relationships and algorithms, creating tensions between actuarial principles, regulatory requirements, and societal expectations. This keynote examines fairness principles, regulatory frameworks, quantitative metrics, fairness testing methodologies, and welfare implications of insurance pricing. Drawing on multidisciplinary perspectives from actuarial science, economics, statistics, and machine learning, it offers a comprehensive view of how anti-discrimination and fairness objectives can be meaningfully and responsibly integrated into modern, data-driven pricing systems, and to highlight open research and policy challenges for the actuarial profession.