Jeff Cai

Patricia and George Scharpf Family Assistant Professor

Mendoza College of Business

University of Notre Dame

Jeff Cai speaking at a lecture — Photo: Alex

A prism-shaped research pipeline connecting AI and agentic systems, decision-making, and knowledge discovery and representation through a rainbow — Inspired by Pink Floyd’s The Dark Side of the Moon.

I am the Patricia and George Scharpf Family Assistant Professor in Real Estate in the IT, Analytics, and Operations Department at the Mendoza College of Business.

Statistical theory powers data science and AI. My research lies at the intersection of statistical machine learning and data-driven decision-making. I develop rigorous statistical methods and practical AI systems that support better decisions by individuals, domain experts, and organizations. I work with companies, NGOs, and healthcare systems to develop and evaluate AI methods in real-world settings. I study their statistical foundations, practical effectiveness, and how people perceive, use, and respond to them.

My work spans statistics, information systems, operations, and finance, with publications in Management Science, The Annals of Statistics, and the Journal of the American Statistical Association, and with Cambridge University Press, and has received multiple paper awards. Previously, I received my Ph.D. in Statistics from The Wharton School of the University of Pennsylvania in 2022.

Academic appointment & background

Patricia and George Scharpf Family Assistant Professor in Real Estate of the IT, Analytics, and Operations Department at the Mendoza College of Business.
Ph.D. in Statistics and Data Science from The Wharton School at the University of Pennsylvania.

Research interests

All publications

Adaptive decision-making and inference: I develop rigorous statistical methods for sequential decision-making (bandits, reinforcement learning), causal and adaptive/selective inference, and experimentation.
Knowledge discovery and representation: I build interpretable methods for learning from networks, tensors, text, and multimodal data, transforming complex structure into reliable knowledge for prediction, inference, and decision-making.
Human–AI and organizational systems: I design and evaluate human-centered and agentic AI systems that augment judgment in expert settings and support decision-making, coordination, and governance in organizations.

My work combines statistical theory, algorithm design, empirical analysis, and real-world experiments, with applications in revenue management, entrepreneurship, finance, organizational governance, and healthcare/mental health.

Teaching

Courses & materials

Current course

Machine Learning in Urban Analysis

I am passionate about teaching and have taught AI and statistical machine learning across a wide range of levels, from pre-college and undergraduate students to graduate students, MBAs, and executive education. My teaching has been recognized with awards at both Mendoza and Wharton. Currently, I teach Machine Learning in Urban Analysis in spring semesters at Mendoza.