A consultant is preparing to enable AI-driven lead scoring for a sales org whose Dynamics 365 instance has accumulated years of manually entered leads, many of which are duplicates of the same contact from repeated marketing campaigns. Before turning on scoring, what should the consultant prioritize?
Select an answer to reveal the explanation.
Short Explanation
AI scoring is only ever as good as the data it learns from, so if the same contact shows up five times under five different campaign records, the model is effectively being taught that this pattern of behavior happens five times as often as it really does. That distortion does not go away on its own, so flipping the feature on and hoping the model figures out the duplicates over time just bakes the problem in from day one. Throwing out every lead that came from marketing is overcorrecting in the wrong direction, since marketing-sourced leads are often perfectly good leads, the issue is the duplication, not the source. And raising the bar for which leads get routed to a rep only changes who sees the already-skewed scores, it does not fix the skew itself. The right move is to clean up the records first, so whatever model gets trained afterward is learning from an accurate picture rather than an inflated one.
Full Explanation
The correct answer is A. AI-driven lead scoring learns patterns from the historical data it is trained on, so duplicate contact records skew those patterns by overrepresenting certain attributes and outcomes; cleansing and deduplicating the data before enabling scoring ensures the model learns from distinct, accurate records and produces reliable scores. Option B is incorrect because scoring models do not inherently detect or discount duplicate records as training noise; the duplicates would continue to distort the training data indefinitely rather than being learned away. Option C is incorrect because marketing-sourced leads are a normal and often valuable source of pipeline, and excluding them wholesale discards legitimate leads instead of addressing the actual problem, which is duplication rather than the source itself. Option D is incorrect because raising the routing threshold only filters which scored leads reach a rep; it does nothing to fix the underlying data quality issue feeding inaccurate scores in the first place. Addressing data quality before enabling the model is the standard prerequisite for reliable AI-driven scoring.