But which member models actually make the ensemble better?
Note
Model importance is to ensemble members what variable importance is to features in a random forest – but measured at the level of whole models.
A model’s importance = how much the ensemble’s accuracy changes when that model is added or removed.
Conceptual illustration (three models). Stars = accuracy by a positively-oriented score, e.g. -WIS.
Compare the full ensemble to the ensemble with one model removed.
Example with n=3: to score model 1, build the ensemble of \{2,3\} and compare it to \{1,2,3\}.
Example with n=3, scoring model 1: take every subset without model 1 — \{2\}, \{3\}, \{2,3\} — and for each compare the ensemble with model 1 added vs. without it (F^{S \cup \{1\}} vs F^{S}), then aggregate.
modelimportance R packagemodel_importance() returns a per-task importance score for each ensemble member.hubUtils, hubEnsembles, hubEvals), so it drops straight into existing hubs.print(), summary(), aggregate().0 importance for those tasksmodelimportance makes this a one-function, hubverse-native analysis.Model importance