Causal Modeling for Fairness in Dynamical Systems
This work addresses fairness concerns in dynamic systems like lending and education, but it is incremental as it builds on existing causal fairness literature by extending it to dynamical settings.
The paper tackles the problem of ensuring fairness in machine learning systems that interact with dynamically changing environments, such as lending and online recommenders, by proposing causal directed acyclic graphs (DAGs) as a unifying framework to compute interventional quantities for short- and long-term outcomes at group and individual levels.
In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups. We discuss causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in such dynamical systems. We show that this formulation affords several new directions of inquiry to the modeler, where causal assumptions can be expressed and manipulated. We emphasize the importance of computing interventional quantities in the dynamical fairness setting, and show how causal assumptions enable simulation (when environment dynamics are known) and off-policy estimation (when dynamics are unknown) of intervention on short- and long-term outcomes, at both the group and individual levels.