CERTIFIED-MACHINE-LEARNING-PROFESSIONAL · Question #41
CERTIFIED-MACHINE-LEARNING-PROFESSIONAL Question #41: Real Exam Question with Answer & Explanation
The correct answer is E: Feature drift. Feature drift (E) is correct because the input variable "expected temperature" has moved outside the range seen during training - the feature distribution has shifted, not the underlying relationship between features and target. Label drift (A) would mean the distribution of the
Question
A data scientist has developed a model to predict ice cream sales using the expected temperature and expected number of hours of sun in the day. However, the expected temperature is dropping beneath the range of the input variable on which the model was trained. Which of the following types of drift is present in the above scenario?
Options
- ALabel drift
- BNone of these
- CConcept drift
- DPrediction drift
- EFeature drift
Explanation
Feature drift (E) is correct because the input variable "expected temperature" has moved outside the range seen during training - the feature distribution has shifted, not the underlying relationship between features and target. Label drift (A) would mean the distribution of the target variable (ice cream sales) has changed. Concept drift (C) would mean the relationship between features and sales has changed (e.g., people no longer buy ice cream on hot days), which isn't described here. Prediction drift (D) is not a standard drift category - predictions may change as a result of feature drift, but that's an effect, not a cause. "None of these" (B) is wrong because drift is clearly present.
Memory tip: Think of drift categories by what changes - Feature = Feed-in data shifts, Concept = Causal relationship shifts, Label = Loop output distribution shifts. Here the thermometer reading (a feature) went out of bounds → Feature drift.
Community Discussion
No community discussion yet for this question.