Mathematical modeling of innovation diffusion has attracted strong academic interest since the early 1960s. Traditional diffusion models have aimed at empirical generalizations and hence describe the spread of new products parsimoniously at the market level. More recently, agent-based modeling and simulation has increasingly been adopted since it operates on the individual level and, thus, can capture complex emergent phenomena highly relevant in diffusion research. Agent-based methods have been applied in this context both as intuition aids that facilitate theory-building and as tools to analyze real-world scenarios, support management decisions and obtain policy recommendations. This review addresses both streams of research. We critically examine the strengths and limitations of agent-based modeling in the context of innovation diffusion, discuss new insights agent-based models have provided, and outline promising opportunities for future research. The target audience of the paper includes both researchers in marketing interested in new findings from the agent-based modeling literature and researchers who intend to implement agent-based models for their own research endeavors. Accordingly, we also cover pivotal modeling aspects in 123 184 E. Kiesling et al. depth (concerning, e.g., consumer adoption behavior and social influence) and outline existing models in sufficient detail to provide a proper entry point for researchers new to the field.

No abstract

No abstract

This paper reviews the literature on quantitative modelling for research and development (R&D) project selection and resource allocation. The topic has been a subject of operations research for about four decades. Its importance stems from the fact that R&D projects are a core element of corporate renewal, heavily influence a firm's market success and, if not properly chosen and trimmed, may waste large amounts of resources or even ruin the enterprise. Our survey classifies and characterizes the various modelling approaches.