Causal drivers of dynamic networks
Dynamic networks models describe temporal interactions between social actors, and as such have been used to describe financial fraudulent transactions, dispersion of destructive invasive species across the globe, and the spread of fake news. An important question in all of these examples is what are the causal drivers underlying these processes. Current network models are exclusively descriptive and based on correlative structures. In this paper we propose a causal extension of dynamic network modelling. In particular, we prove that the causal model satisfies a set of population conditions that uniquely identifies the causal drivers. The empirical analogue of these conditions provide a consistent causal discovery algorithm, which distinguishes it from other inferential approaches. Crucially, data from a single environment is sufficient. We apply the method in an analysis of bike sharing data in Washington D.C. in July 2023.