A distribution conglomerate sells enterprise software subscriptions through one division and low-cost retail hardware through a separate division, and both divisions share a single Dynamics 365 Sales environment. A consultant enabling predictive lead scoring notices that a single scoring model trained across both divisions performs poorly, because the buying signals that predict a software deal have little relationship to what predicts a hardware sale. What should the consultant recommend?
Select an answer to reveal the explanation.
Short Explanation
Picture two very different shopping trips, one where the deciding factor is a long evaluation with multiple stakeholders, and one where someone just wants the cheapest option that ships fast. A single model trying to learn from both trips at once ends up confused, because what predicts success in one has nothing to do with what predicts success in the other. The fix isn't to water down the scoring so everything looks similarly promising, drop one of the businesses from scoring altogether, or assume only one model can ever exist. It's to split the training data along the line that actually separates the two businesses, so each one gets a model trained on the patterns that genuinely apply to it.
Full Explanation
The correct answer is C. Because the software division and the hardware division have fundamentally different buying signals, a single model trained across both blends unrelated patterns together and produces weaker predictions for each; segmenting the training data, for example by business unit or product line, lets Dynamics 365 Sales train and score a model that reflects the actual behavior of each division's buyers. Option A is incorrect because predictive scoring is not limited to a single model per environment; segmentation is supported precisely for cases like this one. Option B is incorrect because lowering the confidence threshold would just make more leads across both divisions get graded Hot regardless of merit, masking the underlying problem instead of fixing the mismatch between divisions. Option D is incorrect because dropping the hardware division from scoring entirely leaves that team without any predictive prioritization at all, which is a worse outcome than giving each division its own properly trained model.