Understanding Fixed Predictions via Confined Regions
This addresses the issue of fairness and recourse in ML for individuals affected by fixed predictions, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of fixed predictions in machine learning models that prevent individuals from changing their outcomes, and it introduces a new paradigm using confined regions to identify such predictions, enabling certification for out-of-sample data and interpretable descriptions.
Machine learning models can assign fixed predictions that preclude individuals from changing their outcome. Existing approaches to audit fixed predictions do so on a pointwise basis, which requires access to an existing dataset of individuals and may fail to anticipate fixed predictions in out-of-sample data. This work presents a new paradigm to identify fixed predictions by finding confined regions of the feature space in which all individuals receive fixed predictions. This paradigm enables the certification of recourse for out-of-sample data, works in settings without representative datasets, and provides interpretable descriptions of individuals with fixed predictions. We develop a fast method to discover confined regions for linear classifiers using mixed-integer quadratically constrained programming. We conduct a comprehensive empirical study of confined regions across diverse applications. Our results highlight that existing pointwise verification methods fail to anticipate future individuals with fixed predictions, while our method both identifies them and provides an interpretable description.