85.7k views
2 votes
Consider the following transaction dataset.

T₁: a, d, e
T₂: a, b, c, e
T₃: a, b, d, e
T₄: a, c, d, e
T₅: b, c, e
T₆: b, d, e
T₇: c, d
T₈: a, b, d

Compute the support for itemsets {e}, {b, d}, and {b, d, e}.

User Catsky
by
7.9k points

1 Answer

4 votes

Final answer:

To compute the support for itemsets {e}, {b, d}, and {b, d, e}, count the number of transactions in which these itemsets appear. The support for {e} is 100%, {b, d} is 50%, and {b, d, e} is 25%.

Step-by-step explanation:

To compute the support for itemsets {e}, {b, d}, and {b, d, e}, we need to count the number of transactions in which these itemsets appear.

The itemset {e} appears in all the transactions, so its support is 100% or 8 out of 8 transactions.

For the itemset {b, d}, we count the number of transactions containing both items. In this case, it appears in 4 transactions: T₃, T₆, T₈, and T₉. So, the support for {b, d} is 4 out of 8 transactions, or 50%.

Finally, for the itemset {b, d, e}, we count the number of transactions containing all three items. It appears in 2 transactions: T₃ and T₆. Therefore, the support for {b, d, e} is 2 out of 8 transactions, or 25%.

The support of an itemset is defined as the proportion of transactions in the dataset which contain the itemset. To compute the support, count the number of transactions that include the itemset and then divide it by the total number of transactions.

For the itemset {e}, it appears in T₁, T₂, T₃, T₄, T₅, and T₆. This means the item {e} appears in 6 out of 8 transactions, so the support for {e} is 6/8 or 75%.

The itemset {b, d} appears together in T₃, T₆, and T₈. Therefore, the support for {b, d} is 3/8 or 37.5%.

Lastly, the itemset {b, d, e} appears in T₃ and T₆, resulting in a support of 2/8 or 25%.

User Luca Frank Guarini
by
7.7k points