LLM-Based Multi-Agent System for Simulating and Analyzing Marketing and Consumer Behavior

TL;DR

This paper presents a novel multi-agent simulation framework powered by large language models to better emulate consumer behavior and social interactions, aiding marketing strategy testing with more realistic and flexible models.

Contribution

It introduces an LLM-based multi-agent system that models complex consumer decision-making and social dynamics without predefined rules, enhancing simulation realism over traditional rule-based models.

Findings

Effective in simulating consumer decisions in marketing scenarios

Reveals emergent social patterns beyond traditional models

Provides actionable insights for marketing strategy testing

Abstract

Simulating consumer decision-making is vital for designing and evaluating marketing strategies before costly real-world deployment. However, post-event analyses and rule-based agent-based models (ABMs) struggle to capture the complexity of human behavior and social interaction. We introduce an LLM-powered multi-agent simulation framework that models consumer decisions and social dynamics. Building on recent advances in large language model simulation in a sandbox environment, our framework enables generative agents to interact, express internal reasoning, form habits, and make purchasing decisions without predefined rules. In a price-discount marketing scenario, the system delivers actionable strategy-testing outcomes and reveals emergent social patterns beyond the reach of conventional methods. This approach offers marketers a scalable, low-risk tool for pre-implementation testing, reducing reliance on time-intensive post-event evaluations and lowering the risk of underperforming campaigns.