Predicting Behaviors with Large Language Model (Llm)-Powered Digital Twins of Customers

Place: Room 3.216 - Grand Paris Campus & online
Time: 12.00-01.30 PM

Speaker: Xin (Shane) Wang, Professor of Marketing – Virginia Tech.

Discussant: Natasha Gilani, Head of AI Accelerator, Hilti

Digital twins of customers (DToC) have emerged as a promising approach to simulate consumer thinking, feeling, and decision-making in marketing contexts. This research proposes and empirically tests a methodological framework that combines fine-tuning and retrieval-augmented generation (RAG) to construct LLM-based customer digital twins. Fine-tuning on user-generated content allows the model to internalize individual traits, preferences, and behaviors, while RAG equips the twin with real-time access to contextual product information. We demonstrate the framework using Amazon e-commerce data, constructing 306 personified digital twins and evaluating their performance in predicting both purchase decisions and review contents. The resulting digital twins achieve high accuracy in predicting future purchases (83%) and generate product reviews with strong semantic alignment to actual customer content (cosine similarity above 0.94). This method opens new possibilities for personalized marketing, pre-deployment campaign testing, and privacy-compliant consumer modeling. The findings contribute to emerging literature on generative AI and synthetic agents in marketing, advancing the conceptual and technical foundation for predictive, interactive, and individualized customer simulation.
 

Biography of the speaker: Shane Wang is a Professor of Marketing at Pamplin College of Business, Virginia Tech University. His research examines how emerging technologies transform business strategy and consumer behavior. Currently, his work and teaching focus on AI agents and synthetic data, with an emphasis on their strategic impact on businesses and consumer markets. His work has appeared in Marketing Science, Journal of Marketing Research, Journal of Marketing, Journal of Consumer Research, Management Science and International Journal of Research in Marketing. Shane has been recognized as one of the Top 50 Most Productive Marketing Scholars (based on the number of publications on the four premier marketing journals: Journal of Consumer Research, Journal of Marketing, Journal of Marketing Research and Marketing Science), calculated by the American Marketing Association. Shane was named to the MSI Young Scholar (2021) and the MSI Scholar (2024). Shane is a member of the academic council at the American Marketing Association and serves as the Vice Chair of Education and Training for the AMA AI Special Interest Group. He currently serves as Senior Editor for Production and Operations Management and as Associate/Area Editor for the Journal of Marketing, Journal of the Academy of Marketing Science, International Journal of Research in Marketing, and Journal of Retailing. He is also a member of the editorial review boards for the Journal of Marketing Research and Journal of Consumer Research.

For further information, please contact Professor Margherita Pagani: margherita.pagani@skema.edu