Many modern extinction drivers are shared with past mass extinction events, such as rapid climatewarming, habitat loss, pollution, and invasive species. This commonality presents a key question:can the extinction risk of species during past mass extinction events inform our predictions for amodern biodiversity crisis? To investigate if it is possible to establish which species were more likelyto go extinct during mass extinctions, we applied a functional trait-based model of extinction riskusing a machine learning algorithm to datasets of marine fossils for the end-Permian, end-Triassicand end-Cretaceous mass extinctions. Extinction selectivity was inferred across each individualmass extinction event, before testing whether the selectivity patterns obtained could be usedto ‘predict’ the extinction selectivity exhibited during the other mass extinctions. Our analysesshow that, despite some similarities in extinction selectivity patterns between ancient crises, theselectivity of mass extinction events is inconsistent, which leads to a poor predictive performance.This lack of predictability is attributed to evolution in marine ecosystems particularly duringMesozoic Marine Revolution, associated with shifts in community structure alongside coincidentEarth system changes. Our results suggest that past extinctions are unlikely to be informative forpredicting extinction risk during a projected mass extinction.