Collective dynamics of strategic classification

TL;DR

This paper uses evolutionary game theory to analyze how strategic users and adaptive algorithms interact in high-stakes AI decision-making, revealing complex feedback loops and potential mitigation strategies.

Contribution

It introduces a rigorous framework for studying the feedback dynamics between strategic users and institutions, including interventions like detection and recourse to improve outcomes.

Findings

Improved detection reduces social costs and encourages user improvement.

Algorithmic recourse can steer dynamics towards better user performance.

Re-adaptation speed influences the final strategic equilibrium.

Abstract

Classification algorithms based on Artificial Intelligence (AI) are nowadays applied in high-stakes decisions in finance, healthcare, criminal justice, or education. Individuals can strategically adapt to the information gathered about classifiers, which in turn may require algorithms to be re-trained. Which collective dynamics will result from users' adaptation and algorithms' retraining? We apply evolutionary game theory to address this question. Our framework provides a mathematically rigorous way of treating the problem of feedback loops between collectives of users and institutions, allowing to test interventions to mitigate the adverse effects of strategic adaptation. As a case study, we consider institutions deploying algorithms for credit lending. We consider several scenarios, each representing different interaction paradigms. When algorithms are not robust against strategic manipulation, we are able to capture previous challenges discussed in the strategic classification literature, whereby users either pay excessive costs to meet the institutions' expectations (leading to high social costs) or game the algorithm (e.g., provide fake information). From this baseline setting, we test the role of improving gaming detection and providing algorithmic recourse. We show that increased detection capabilities reduce social costs and could lead to users' improvement; when perfect classifiers are not feasible (likely to occur in practice), algorithmic recourse can steer the dynamics towards high users' improvement rates. The speed at which the institutions re-adapt to the user's population plays a role in the final outcome. Finally, we explore a scenario where strict institutions provide actionable recourse to their unsuccessful users and observe cycling dynamics so far unnoticed in the literature.