Stochastic Agent-Based Simulations of Social Networks

The rapidly growing field of network analytics requires data sets for use in evaluation. Real world data often lack truth and simulated data lack narrative fidelity or statistical generality. This paper presents a novel, mixed-membership, agentbased simulation model to generate activity data with narrative power while providing statistical diversity through random draws. The model generalizes to a variety of network activity types such as Internet and cellular communications, human mobility, and social network interactions. The simulated actions over all agents can then drive an application specific observational model to render measurements as one would collect in real-world experiments. We apply this framework to human mobility and demonstrate its utility in generating high fidelity traffic data for network analytics.