A sales manager complains that leads graded Warm under Dynamics 365 Sales predictive scoring rarely convert for her team, while the underlying numeric scores actually track conversion reasonably well. She asks the consultant to fix the mismatch between the label and reality without retraining or replacing the model. What should the consultant do?

The correct action is to adjust the score band thresholds, the numeric ranges that map to Hot, Warm, and Cool, so the labels better match this team's conversion outcomes. The Hot, Warm, and Cool labels are named ranges applied on top of the numeric score, and those ranges are configurable independently of the underlying model, so the consultant can move the boundary between Warm and Cool upward until the label reflects where this team's leads actually stop converting well. Retraining the entire predictive model on a fresh data export is incorrect because retraining addresses the accuracy of the numeric score itself, which the manager already says is fine; the problem is purely how that score gets labeled, and retraining would not touch the band configuration. It is also incorrect to claim that band labels are hard-coded into the model and cannot be changed separately. Asking sellers to manually overwrite the grade shown on each lead is incorrect because it is a one-off patch that does not scale, has to be repeated indefinitely, and leaves the systemic threshold problem in place for every new lead that arrives. Disabling predictive scoring and switching to a manual point-based rule is incorrect on its premise: band thresholds are reconfigurable while the model stays live, so there is no need to abandon predictive scoring in favor of a manual rule just to fix a labeling boundary. The right move is a settings change, not a data change, a manual workaround, or a feature replacement.