Reproduce “LLM-Based Multi-Agent System for Simulating and Analyzing Marketing and Consumer Behavior” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Man-Lin Chu, Lucian Terhorst, Kadin Reed, Tom Ni, Weiwei Chen, Rongyu Lin
Researchers from Clark University and Quinnipiac University developed an LLM-powered multi-agent simulation framework to model consumer decision-making and social dynamics in response to marketing interventions. The framework successfully simulated the effects of a price discount, leading to a 51% revenue increase for the promoted shop and demonstrating emergent consumer habits and word-of-mouth information diffusion among agents.
Key insights
- LLM-powered generative agents can realistically simulate complex and emergent consumer behaviors, including habit formation, social influence, and context-sensitive decision-making.
- The framework provides a proactive, low-risk, and scalable environment for pre-implementation testing of marketing strategies, yielding actionable insights for businesses.
- Simulation results align with established marketing and economic theories regarding price sensitivity, market share shifts, and the diffusion of information through social networks.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.