A consultant is deploying predictive lead scoring for a conglomerate that sells low-cost transactional products with a two-week sales cycle alongside complex enterprise solutions with a nine-month sales cycle, all tracked in the same Dynamics 365 Sales environment. The sales director wants a single predictive score to reliably prioritize leads across both business lines. What should the consultant advise?
Select an answer to reveal the explanation.
Short Explanation
Picture trying to teach one forecaster to predict both a two-week sprint and a nine-month marathon using the same playbook, there's a real chance the patterns that matter for one just don't apply to the other. So the honest answer here isn't to assume a single score will serve both business lines equally well, it's to flag that risk up front and then actually check it, by watching whether leads graded a certain way in each line convert at the rate you'd expect. That's a much better foundation than either blind faith or an overcorrection. Blind faith looks like just turning the feature on and hoping it generalizes across wildly different sales cycles without checking. The overcorrection in the other direction would be training the model only on the faster-converting product line and then handing that same score to the slower, more complex one, that just imports one population's patterns into a population they don't fit. And swinging all the way to shutting the feature off entirely throws away real value over what's really a monitoring question, not a reason to abandon it.
Full Explanation
The correct answer is A. A model trained on a mix of two populations with very different conversion timelines and patterns risks learning a blended signal that fits neither business line particularly well, so raising that risk with the director and then validating it by tracking conversion rate against grade separately for each line is the responsible path; it gives the client real evidence about whether the single score is actually serving both, rather than assuming it will. Option B is incorrect because it dismisses a real risk without evidence; a nine-month enterprise cycle and a two-week transactional cycle do not necessarily share the same behavioral signals, and assuming generalization without checking invites unreliable scores for one or both lines. Option C is incorrect because training exclusively on the transactional product's faster-converting leads would build a model shaped by that population's patterns and then misapply it to the structurally different enterprise leads, which is likely to produce worse results than the original mixed approach. Option D is incorrect because it overreacts to the concern; disabling the feature entirely discards its value for the whole environment when the actual issue is that the model's fit needs to be checked and monitored per business line, not eliminated outright.