ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values

arXiv:2604.11200v1 Announce Type: cross Abstract: Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's loan approval rate), so understanding their causes can be crucial. We propose \ours{}: a Shapley value method for attributing prediction shifts to changes in the conditional probabilities of interpretable subgroups of data, where these subgroups are defined by the stru