Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses

TL;DR

This paper introduces a novel method leveraging strategic responses to machine learning models as instrumental variables to recover causal relationships despite unobserved confounding, improving fairness and decision quality.

Contribution

It establishes a new connection between strategic responses and IV regression, enabling causal inference in strategic settings with unobserved confounders.

Findings

The sequence of deployed models acts as an instrument affecting observable features.

The method improves individual fairness and agent outcomes.

Deviating from causal coefficients can cause unbounded unfairness.

Abstract

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.