Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty

Valia Efthymiou, Chara Podimata, Diptangshu Sen, Juba Ziani

Keywords: strategic classification, causality, uncertainty, desirable effort, classifier design

TL;DR: This work studies the problem of designing classifiers that can incentivize strategic agents to exert effort in desirable features even when they have incomplete information about the classifier or the causal graph.

Abstract: We study strategic classification in binary decision-making settings where agents can modify their features in order to improve their classification outcomes. Importantly, our work considers the causal structure across different features, acknowledging that effort in one feature may affect other features. The main goal of our work is to understand when and how much agent effort is invested towards desirable features, and how this is influenced by the deployed classifier, the causal structure of the agent's features, their ability to modify them, and the information available to the agent about the classifier and the feature causal graph. We characterize conditions under which agents with full information about the causal structure and the principal's classifier align with the principal's goals of incentivizing effort mostly in ``desirable'' features, and identify cases where designing such classifiers (from the principal's side) is still tractable despite general non-convexity. Under incomplete information, we show that uncertainty leads agents to prioritize features with high expected impact and low variance, which may often be misaligned with the principal's goals. Finally, using numerical experiments based on a cardiovascular disease risk study, we illustrate how to incentivize desirable modifications even under uncertainty.

Primary Area: Social and economic aspects of machine learning (e.g., fairness, interpretability, human-AI interaction, privacy, safety, strategic behavior)

Submission Number: 21784