Modeling the Diffusion of Innovations Through Small-World Networks

Abstract

We explore how the structure of connections between members of a target population systematically influences the time-path of diffusion of an innovation through that population. Using the formalisms of small world networks, we model the existence of potential connections between members of a target population, the mechanisms for the activation of connections, and the effect of an activation (i.e., whether it leads to an adoption). Our proposed Small-World Multiple Influence model nests the Bass model and the Non-uniform influence model, and allows us to decompose word-of-mouth effects, e.g., whether an innovation spreads due to strong collective influence of a small circle of family members and friends or through the strong influence of distant acquaintances. The model incorporates a stochastic network, enables aggregation of individual-level adoptions in a network into a population diffusion curve, and permits unbiased estimation of the parameters of an underlying social network from a population diffusion curve. We assess the validity and value of our model by using data from 35 new products introduced in the US, and from diffusion data for cell phone and Internet from several European countries. The results show that the proposed model outperforms the competing models on both theoretical and empirical criteria.