<ul><li>Deferring systems extend supervised Machine Learning (ML) models with the possibility to defer predictions to human experts.</li><li>This paper evaluates the impact of deferring strategies on system accuracy through a causal lens.</li><li>The potential outcomes framework for causal inference is linked with deferring systems to identify the causal impact of the deferring strategy on predictive accuracy.</li><li>The approach is evaluated on synthetic and real datasets for seven deferring systems from the literature.</li></ul>

A Causal Framework for Evaluating Deferring Systems

Discover more