Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
This work addresses the problem of incentivizing desirable agent behavior in strategic classification for decision-makers, but it is incremental as it builds on existing frameworks by incorporating causality and uncertainty.
The paper tackles strategic classification where agents modify features to improve outcomes, considering causal structures and uncertainty. It derives conditions for agents to focus on desirable features under complete information, shows classifier design is generally non-convex but tractable in special cases, and finds that uncertainty leads agents to prioritize features with higher expected importance and lower variance, potentially misaligning with principal preferences.
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 a given feature may affect other features. The main goal of our work is to understand \emph{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. In the complete information case, when agents know the classifier and the causal structure of the problem, we derive conditions ensuring that rational agents focus on features favored by the principal. We show that designing classifiers to induce desirable behavior is generally non-convex, though tractable in special cases. We also extend our analysis to settings where agents have incomplete information about the classifier or the causal graph. While optimal effort selection is again a non-convex problem under general uncertainty, we highlight special cases of partial uncertainty where this selection problem becomes tractable. Our results indicate that uncertainty drives agents to favor features with higher expected importance and lower variance, potentially misaligning with principal preferences. Finally, numerical experiments based on a cardiovascular disease risk study illustrate how to incentivize desirable modifications under uncertainty.