Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
This addresses the challenge of ensuring fair and accurate decision-making in automated systems where individuals adapt strategically, offering a method to improve fairness, outcomes, and predictive risk, though it is incremental in applying instrumental variable regression to a new context.
The paper tackles the problem of strategic manipulation of features by individuals in response to ML decision rules, showing that such strategic responses can be leveraged to recover causal relationships between features and outcomes, even with unobserved confounders, by treating the sequence of deployed models as an instrumental variable.
In settings where Machine Learning (ML) algorithms automate or inform consequential decisions about people, individual decision subjects are often incentivized to strategically modify their observable attributes to receive more favorable predictions. As a result, the distribution the assessment rule is trained on may differ from the one it operates on in deployment. While such distribution shifts, in general, can hinder accurate predictions, our work identifies a unique opportunity associated with shifts due to strategic responses: We show that we can use strategic responses effectively to recover causal relationships between the observable features and outcomes we wish to predict, even under the presence of unobserved confounding variables. Specifically, our work establishes a novel connection between strategic responses to ML models and instrumental variable (IV) regression by observing that the sequence of deployed models can be viewed as an instrument that affects agents' observable features but does not directly influence their outcomes. We show that our causal recovery method can be utilized to improve decision-making across several important criteria: individual fairness, agent outcomes, and predictive risk. In particular, we show that if decision subjects differ in their ability to modify non-causal attributes, any decision rule deviating from the causal coefficients can lead to (potentially unbounded) individual-level unfairness.