Causal Inference out of Control: Estimating the Steerability of Consumption
This work addresses a critical issue for regulators and academics in digital platforms, offering a novel framework for causal inference in dynamic settings, though it is incremental in combining control theory with existing causal methods.
The paper tackles the problem of estimating the causal effect of algorithmic platform actions on consumption, introducing the concept of 'steerability of consumption' and proposing a method that weakens unrealistic overlap assumptions by modeling consumption dynamics over time. The result is a set of sufficient conditions for causal identifiability, demonstrated through examples from econometrics, macroeconomics, and machine learning.
Regulators and academics are increasingly interested in the causal effect that algorithmic actions of a digital platform have on consumption. We introduce a general causal inference problem we call the steerability of consumption that abstracts many settings of interest. Focusing on observational designs and exploiting the structure of the problem, we exhibit a set of assumptions for causal identifiability that significantly weaken the often unrealistic overlap assumptions of standard designs. The key novelty of our approach is to explicitly model the dynamics of consumption over time, viewing the platform as a controller acting on a dynamical system. From this dynamical systems perspective, we are able to show that exogenous variation in consumption and appropriately responsive algorithmic control actions are sufficient for identifying steerability of consumption. Our results illustrate the fruitful interplay of control theory and causal inference, which we illustrate with examples from econometrics, macroeconomics, and machine learning.