All MCQs

As itemset size grows, short or nonmatching transactions cannot contribute support.
Removing them reduces later scan cost.

Hash trees organize candidates into buckets for efficient matching.
Transactions can be mapped to relevant candidate subsets during scans.

A consistent lexicographic order gives itemsets a canonical form.
This simplifies joins, subset checks, and duplicate control.

Lk consists of k-itemsets meeting minimum support.
It is used to generate candidates for the next level.

Ck contains itemsets being considered at level k.
After support filtering, qualifying sets form Lk.

Dense data produce many possible combinations and long candidates.
Apriori must enumerate and count a large search space.

Dense datasets and low support thresholds cause candidate explosion.
Memory use and repeated counting can become prohibitive.

Each level typically generates new candidates and counts their occurrences.
This scan-intensive behavior can be expensive for large datasets.

A candidate with an infrequent subset cannot be frequent.
This follows directly from the Apriori property.

Compatible (k-1)-itemsets are united to create k-itemset candidates.
Prefix ordering prevents many duplicates.

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

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