In August 2022 the Department of Health and Human Services (HHS) issued a notice of
proposed rulemaking prohibiting covered entities, which include health care providers and …

Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Recent scholarship has brought attention to the fact that there often exist multiple models for
a given prediction task with equal accuracy that differ in their individual-level predictions or …

Automated decision systems are increasingly used to take consequential decisions in
problems such as job hiring and loan granting with the hope of replacing subjective human …

Predictive multiplicity occurs when classification models with statistically indistinguishable
performances assign conflicting predictions to individual samples. When used for decision …

Decision makers, such as doctors, judges, and managers, make consequential choices
based on predictions of unknown outcomes. Do these decision makers make systematic …

The Rashomon Effect, coined by Leo Breiman, describes the phenomenon that there exist
many equally good predictive models for the same dataset. This phenomenon happens for …

Abstract Machine learning tasks may admit multiple competing models that achieve similar
performance yet produce conflicting outputs for individual samples---a phenomenon known …

The fundamental problem of causal inference--that we never observe counterfactuals--
prevents us from identifying how many might be negatively affected by a proposed …

We show that lenders face more uncertainty when assessing default risk of historically under-
served groups in US credit markets and that this information disparity is a quantitatively …