Which of the following is a simple statistic to monitor for categorical feature drift?
Select an option, then click Submit answer.
Reference / correct answer:
Mode, number of unique values, and percentage of missing values
Most accepted answer: C. Mode, number of unique values, and percentage of missing values
Community votes: A=2, C=5
Selected Answer: C C is the correct answer upvoted 1 times
Selected Answer: C For categorical features, a simple and low-cost way to monitor drift is to track: Mode (most frequent category) Number of unique values (cardinality) Percentage of missing values These give quick insights into distribution changes without heavy computation. upvoted 2 times
Selected Answer: C C over A because it's a crap question but I think the intent here is the most practical considering it's still low cost upvoted 1 times
Selected Answer: A Either the question is badly worded (it's in the singular) or it's a trick question. But the most appropriate simple *single* statistic would be the mode. C is multiple statistics :-? upvoted 2 times
Selected Answer: C Categorical Features ->Summary Statistics: Mode, Number of unique values, Number of missing values upvoted 1 times