The Role of Causal Features in Strategic Classification for Robustness and Alignment
For machine learning researchers studying strategic classification and causal inference, this work provides theoretical insights into when causal classifiers are advantageous and how they can mitigate social costs.
This paper establishes theoretical links between causal models and strategic classification, showing that causal features can lead to optimal classification error after large user adaptation under bounded noise, and can align long-term incentives between institutions and users. Empirical validation on synthetic data supports the theory.
In strategic classification, an institution (e.g., a bank) anticipates adaptation from users who change their features to increase utility in a classification task (e.g., loan repayment). Since a key challenge is the distribution shift induced by users, we turn to causal models, which have been shown to bound the worst-case out-of-distribution (OOD) risk, and establish several new results that link causality and strategic classification. First, we show that causal classification leads to optimal classification error after any sufficiently large adaptation, when the noise is bounded in a certain way. Second, when these assumptions do not hold, we show OOD cross-entropy risk of optimal classifiers decomposes into an OOD bias term and a term arising from not using all observable features, allowing us to understand when causal classifiers have an advantage. Finally, we show that the use of causal features can allow alignment of long-term incentives between institutions and users, contrasting with previous work that highlights social costs of such approaches. We validate our theory empirically on synthetic data, finding that our results predict behavior in practice.