Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
Year: 2026
Type: preprint
Abstract: Understanding how a prediction model will perform in a new environment before deployment is essential to preventing harm when algorithms inform decision-making. Two common sources of model performance degradation are (i) covariate shift, where the target covariate distribution differs from the source, and (ii) selective labels, where the observability of outcomes depends on historical decisions. We study pre-deployment model evaluation under the joint presence of covariate shift and labeling of outcomes selectively based on observed features. In particular, we present a double machine learning procedure for estimating the target risk of an arbitrary black-box prediction model under a general loss function. We show identification of this estimand under standard assumptions and derive a bias-corrected estimator based on the influence function of the target risk. Finally, we evaluate our estimator through experiments using the eICU electronic health records database, showing that it tracks the true target risk more accurately than methods that address either selective labels or covariate shift alone, as well as baselines that combine standard plug-in approaches.
Source: arXiv (Cornell University)
Authors: Ulichney, Annie, Coston, Amanda
Institution: University of California, Berkeley
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
OpenAlex ID: W7164842946
Cites:
Cited by:
Related to: