| Abstract: |
This study introduces an experimental framework leveraging Large Language Models (LLMs) as pre-testing tools for behavioral laboratory experiments. Focusing on prominent behavioral operations management papers published in Management Science, particularly in the areas of inventory management, forecasting, and sourcing, we developed an experimental framework that utilizes LLMs to simulate human behavior and decision-making in a laboratory setting. Through a structured system of prompts and iterative game rounds, we demonstrate the feasibility and validity of using LLMs as a pre-testing tool for behavioral lab experiments. Our empirical analysis confirms that LLMs not only replicate human decision patterns but also exhibit stability and consistency.
|
|
Biography:
|
Jing Wu is an Associate Professor in the Department of Decision Sciences and Managerial Economics at the Chinese University of Hong Kong (CUHK) Business School. He is the Director of the Asian Institute of Supply Chains & Logistics (AISCL)’s Institute Development Office. He receives his Ph.D. (major in operations management, minor in economics & finance) and MBA from the University of Chicago Booth School of Business and his bachelor’s degree in Electronic Engineering from Tsinghua University. Professor Wu’s primary research fields are the operations-finance interface, global supply chains, FinTech, and business intelligence. His papers are published in leading journals such as Management Science, M&SOM, and POMS. His articles appear in business magazines such as MIT Sloan Management Review, the Economist, and Forbes. His quantitative research on the supply chain impact of COVID-19 and the Trade War has been reported by over 400 media outlets in over 20 countries worldwide. He is a senior editor for POMS, and serves as a committee/track/cluster chair for INFORMS, POMS, and several other leading international academic conferences. Before academia, he worked as a quantitative strategist at Deutsche Bank, New York.
|
