Question

A database has five transactions, where each letter, such as "M", represents an item: T_1 = {M, O, N, K, E, Y}; T_2 = {D, O, N, K, E, Y}; T_3 = {M, A, K, E}; T_4 = {M, U, C, K, Y}; T_5 = {C, O, K, I, E}; Let min-sup = 60% and min-conf = 80%, then Find all frequent itemsets; List all of the strong association rules (with support s greaterthanorequalto min-sup and c greaterthanorequalto min-conf) matching the following meta-rule, where X is a variable representing customers and item_i denotes variables of items: forall X, buy(X, item_1) lambda buy(X, item_2) rightarrow buy(X, item_3) [s, c]

Answer 1

1 ans:

About data scan: Apriori needs to scan the database repeatedly to accumulate a k-item support and check the frequency. On the other hand, FP-growth algorithm needs 2 scan, once to identify frequent1-item set and second to build FP-tree. - About candidate generation: Apriori algorithm generates exponential number of candidate set and the self-join process of candidate generation itself is expensive. FP-growth algorithm does not generate any candidate set. 2 ans: - Buys(X, E) and buys (X, O) rightarrow buys(X, K) [60%, 100%] - Buys(X, O) and buys(X, K) rightarrow buys(X, E) [60%, 100%]

2 ans: