Dean’s Research Colloquium

The Dean’s Research Colloquium gathers faculty members from all disciplines within the LeBow College of Business. The primary goal of the colloquium is to foster interdisciplinary discussions on subjects that have significant and far-reaching consequences for research in economics and business.

Our inaugural colloquium is on “Using Generative AI for Research” and will feature Ayelet Israeli, PhD, from Harvard Business School. Professor Israeli will present her innovative paper which shows how large language models (LLMs) like ChatGPT can be used to generate synthetic consumer responses to typical market research questions. Following the presentation, a panel discussion among LeBow faculty will explore the diverse applications of LLMs for research in economics and business, ranging from pre-testing survey instruments to copy editing articles.

Featured speaker:

Ayelet Israeli, PhD
Marvin Bower Associate Professor
Harvard Business School

Paper:

Brand, Israeli and Ngwe (2023WP) Using GPT for Market Research Large language models (LLMs) have quickly become popular as labor-augmenting tools for programming, writing, and many other processes that benefit from quick text generation. In this paper we explore the uses and benefits of LLMs for researchers and practitioners who aim to understand consumer preferences. We focus on the distributional nature of LLM responses, and query the Generative Pre-trained Transformer 3.5 (GPT-3.5) model to generate hundreds of survey responses to each prompt. We offer two sets of results to illustrate our approach and assess it. First, we show that GPT-3.5, a widely-used LLM, responds to sets of survey questions in ways that are consistent with economic theory and well-documented patterns of consumer behavior, including downward-sloping demand curves and state dependence. Second, we show that estimates of willingness-to-pay for products and features generated by GPT-3.5 are of realistic magnitudes and match estimates from a recent study that elicited preferences from human consumers. We also offer preliminary guidelines for how best to query information from GPT-3.5 for marketing purposes and discuss potential limitations. Read full text.