Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions (Database)

      Marketing Science

Combining Observational and Experimental Data to Improve Efficiency Using Imperfect Instruments

      Marketing Science

The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective

with Olivier Toubia, R&R Marketing Science

Leveraging LLMs to Improve Experimental Design: A Generative Stratification Approach

with Seungwoo, R&R Journal of Marketing Research

Modeling Story Expectations to Understand Engagement: A Generative Framework Using LLMs

with Hortense Fong

Designing Promises with Reference-Dependent Customers: The Case of Online Grocery Delivery Time

with Tilman Drerup

Finding Exogenous Variation in Data

with Eliot Abrams and Ali Hortacsu

AAAI Workshops, 2018

Auction Throttling and Causal Inference of Online Advertising Effects

with Harikesh Nair and Fengshi Niu

EC'22