CIS 671 – Databases II
Homework #5
(
/100)
Due: 11/30/06 before class
Question 1- Association Rules ( /25)
Simulate the running of the Apriori algorithm over the following data set and find the frequent
itemsets with a support threshold 20%:
{A,B,E}, {B,D}, {B,C}, {A,B,D}, {A,C}, {B,C}, {A,C}, {A,B,C,E}, {A,B,C}
(The above data means that items A, B, and E were purchased together in the first transaction; B
and D in the second, and so on)
a) Show the association rules with a confidence threshold of 75 % and a support threshold of
20%.
b) List all possible association rules that can be generated from itemset {A,B,C}?
Question 2- Association Rules ( /20)
Given the following list of transactions, simulate the running of the Apriori algorithm over the
data and report
the association rule(s)
with a confidence threshold of 75 % and a support
threshold of 30 %.
{B,J,P}
{B,P}
{B,M,P}
{R,B}
{R,M}
Question 3- Nearest Neighbor Search over VA-files ( /30)
We have the following data points that are generated from the interval [1.
.25].