Data Mining MCQs

Discretization replaces numeric ranges with bins such as low, medium, and high.
It can simplify patterns but may lose detail.

The value k refers to the number of distinct items in the set.
A three-itemset contains exactly three items.

Confidence uses the antecedent support in its denominator.
Therefore confidence(X → Y) can differ from confidence(Y → X).

Apriori begins by counting individual item frequencies.
Only frequent one-itemsets can participate in larger frequent sets.

Data cleaning improves reliability before modeling.
Poor-quality inputs can create misleading patterns and unstable models.

Equal-width binning partitions the value range uniformly.
It is simple but can create sparse bins for skewed data.

Support count is an absolute frequency.
It shows how many transactions contain all items in the itemset.

Closed itemsets compress frequent-pattern output without losing support information.
Any itemset sharing support with a larger superset is not closed.

The join step combines compatible frequent itemsets.
A subsequent prune step removes candidates with infrequent subsets.

Interval scales support meaningful differences but not meaningful ratios.
Temperature in Celsius is a common example because zero is arbitrary.

Data mining applies computational and statistical methods to reveal actionable structure in data.
Its focus is knowledge discovery rather than simple storage or reporting.

Ratio variables have equal intervals and an absolute zero point.
Examples include weight, distance, and transaction amount.