Linear Classifiers that Encourage Constructive Adaptation
This addresses the issue of strategic adaptation in ML systems for decision subjects, offering a novel approach to encourage constructive changes rather than manipulation.
The paper tackles the problem of strategic behavior in machine learning systems where individuals adapt features to obtain desired outcomes, which leads to performance loss in deployment. The result is a method that maintains accuracy while inducing higher levels of improvement and less manipulation in benchmarks on simulated and real-world datasets.
Machine learning systems are often used in settings where individuals adapt their features to obtain a desired outcome. In such settings, strategic behavior leads to a sharp loss in model performance in deployment. In this work, we aim to address this problem by learning classifiers that encourage decision subjects to change their features in a way that leads to improvement in both predicted \emph{and} true outcome. We frame the dynamics of prediction and adaptation as a two-stage game, and characterize optimal strategies for the model designer and its decision subjects. In benchmarks on simulated and real-world datasets, we find that classifiers trained using our method maintain the accuracy of existing approaches while inducing higher levels of improvement and less manipulation.