A consultant reviews an AI-generated sales forecast for a seasonal retail-supply business and finds that the model has overestimated close probability for Q4 opportunities for two consecutive years, apparently because the training data underrepresents the seasonal slowdown pattern. What should the consultant do?
Select an answer to reveal the explanation.
Short Explanation
When a forecasting model keeps making the same seasonal mistake two years running, that is a strong signal the problem lives in the data it learned from, not in any one quarter's deals. If the training window is too short to have really seen a full seasonal cycle, the model simply never learned that Q4 slows down, so the fix is to widen or adjust that window so the pattern is actually in there for it to learn. Manually overriding every deal's probability by hand every quarter might patch the symptom for one cycle, but it is exhausting and does nothing to stop the same miscalibration from showing up again next year. Turning the whole thing off for the quarter throws away useful signal for every other opportunity that is not part of the seasonal issue, which is a much bigger sacrifice than the problem calls for. And nudging the weight on deal size does not touch seasonality at all, that is solving a different problem entirely. Fixing the training horizon is the change that actually targets what went wrong.
Full Explanation
The correct answer is C. The root cause identified is that the model's training data does not adequately represent the recurring seasonal slowdown, so adjusting or extending the historical window to include enough full seasonal cycles gives the model the pattern it needs to weight Q4 appropriately going forward. Option A is incorrect because manually overriding every opportunity's probability each quarter is a labor-intensive workaround that must be repeated indefinitely and does not correct the underlying model, leaving the same problem to resurface. Option B is incorrect because disabling AI forecasting for an entire quarter discards the value the model provides for the other opportunities and stages within that period, which is a disproportionate response to a data-window problem. Option D is incorrect because deal size is unrelated to the identified issue of seasonal underrepresentation; adjusting that weight would not correct the model's blind spot regarding the recurring Q4 slowdown and could distort scoring for unrelated reasons. Correcting the training data's time horizon is the targeted fix for a seasonally biased model.