Agent-based modeling in marketing: Guidelines for rigor

Agent-based modeling can illuminate how complex marketing phenomena emerge from simple decision rules. Marketing phenomena that are too complex for conventional analytical or empirical approaches can often be modeled using this approach. Agent-based modeling investigates aggregate phenomena by simulating the behavior of individual “agents,” such as consumers or organizations. Some useful examples of agent-based modeling have been published in marketing journals, but widespread acceptance of the agent-based modeling method and publication of this method in the highest-level marketing journals have been slowed by the lack of widely accepted standards of how to do agent-based modeling rigorously. We address this need by proposing guidelines for rigorous agent-based modeling. We demonstrate these guidelines, and the value of agent-based modeling for marketing research, through the use of an example. We use an agent-based modeling approach to replicate the Bass model of the diffusion of innovations, illustrating the use of the proposed guidelines to ensure the rigor of the analysis. We also show how extensions of the Bass model that would be difficult to carry out using traditional marketing research techniques are possible to implement using a rigorous agent-based approach.

► We develop guidelines for the rigorous creation and use of agent-based models.
► We provide suggestions for when to apply agent-based modeling to a phenomenon of interest.
► We illustrate these guidelines and suggestions with an illustrative example in the domain of innovation diffusion.