1
Association Rule Mining
What Is Association Rule Mining?
Association rule mining is finding frequent patterns or associations among sets of items or objects, usually amongst transactional data
Applications include Market Basket analysis, cross-marketing, catalog design, etc.
2
Association Mining
Examples. Rule form: “Body ead [support, confidence]”.
buys(x, “diapers”) buys(x, “beers”) [0.5%, 60%]
buys(x, "bread") buys(x, "milk") [0.6%, 65%]
major(x, "CS") /\ takes(x, "DB") grade(x, "A") [1%, 75%]
age(X,30-45) /\ income(X, 50K-75K) buys(X, SUVcar)
age=“30-45”, income=“50K-75K” car=“SUV”
Market-basket Analysis & Finding Associations
Do items occur together?
Proposed by Agrawal et al in 1993.
It is an important data mining model studied extensively by the database and data mining community.
Assumes all data are categorical.
Initially used for Market Basket Analysis to find how items purchased by customers are related.
Bread Milk [sup = 5%, conf = 100%]
Association Rule: Basic Concepts
Given: (1) database of transactions, (2) each transaction is a list of items (purchased by a customer in a visit)
Find: all rules that correlate the presence of one set of items with that of another set of items
E.g., 98% of people who purchase tires and auto accessories also get automotive services done
Applications
* Maintenance Agreement (What the store should do to boost Maintenance Agreement sales)
Home Electronics * (What other products should the store stocks up?)
Detecting “ping-pong”ing of patients, faulty “collisions”
5
Association Rule Mining
Given a set of transactions, find rules that will predict the occurrence of an item based on the occurrences of other items in the transaction
6
Market-Basket transactions
TID Items
1 Bread, Milk
2 Bread, Diaper, Beer, Eggs
3 Milk, Diaper, Beer, Coke
4 Bread, Milk, Diaper, Beer
5 Bread, Milk, Diaper, Coke
Example of Association Rules
{Diaper} {Beer},
{Milk, Bread} {Eggs,Coke},
{Beer, Bread} {Milk},
Implication means co-occurrence,
not causality!
An itemset is simply a set of items
Examples from a Supermarket
Can you think of association rules from a supermarket?
Let’s say you identify association rules from a supermarket, how might you exploit them?
That is, if you are the store manager, how might you make money?
Assume you have a rule of the form X Y
7
Supermarket examples
If you have a rule X Y, you could:
Run a sale on X if you want to increase sales of Y
Locate the two items near each other
Locate the two items far from each other to make the shopper walk through the store
Print out a coupon on checkout for Y if shopper bought X but not Y
8
Association “rules”–standard format
Rule format: (A set can consist of just a single item)
If {set of items} Then {set of items}
Condition implies Results
If {Diapers, Baby Food}
Condition
{Beer, Chips}
Results
Then
Customer
buys diaper Customer buys both
Customer
buys beer
Right side very often is a single item Rules do not imply causality
What is an Interesting Association?
Requires domain-knowledge validation
Actionable, non-trivial, understandable
Algorithms provide first-pass based on statistics on how “unexpected” an association is
Some standard statistics used:
C R
support ≈ p(R&C) percent of “baskets” where rule holds
confidence ≈ p(R|C) percent of times R holds when C holds
Support and Confidence
Find all the rules X Y with minimum confidence and support Support = probability that a transaction
contains {X,Y}
i.e., ratio of transactions in which X, Y occur together to all transactions in DB.
Confidence = conditional probability that a transaction having X contains Y
i.e., ratio of transactions in which X, Y occur together to those in which X occurs.
Thel confidence of a rule LHS => RHS can be computed as the support of the whole itemset divided by the support of LHS:
Confidence (LHS => RHS) = Support(LHS RHS) / Support(LHS)
Customer
buys diaper Customer buys both
Customer
buys beer
Definition: Frequent Itemset
Itemset
A collection of one or more items
Example: {Milk, Bread, Diaper}
k-itemset: itemset with k items
Support count ()
Frequency count of occurrence of itemset
E.g. ({Milk, Bread,Diaper}) = 2
Support
Fraction of transactions containing the itemset
E.g. s({Milk, Bread, Diaper}) = 2/5
Frequent Itemset
An itemset whose support is greater than or equal to a minsup threshold
TID Items
1 Bread, Milk
2 Bread, Diaper, Beer, Eggs
3 Milk, Diaper, Beer, Coke
4 Bread, Milk, Diaper, Beer
5 Bread, Milk, Diaper, Coke
12
Support and Confidence Calculations
TID Items
1 Bread, Milk
2 Bread, Diaper, Beer, Eggs
3 Milk, Diaper, Beer, Coke
4 Bread, Milk, Diaper, Beer
5 Bread, Milk, Diaper, Coke
Beer}Diaper,Milk{
4.05
2
|T|
)BeerDiaper,,Milk(
s
67.03
2
)Diaper,Milk(
)BeerDiaper,Milk,(
c
Given Association Rule
– {Milk, Diaper} {Beer}
Rule Evaluation Metrics
– Support (s)
Fraction of transactions that contain both X and Y
– Confidence (c)
Measures how often items in Y appear in transactions that contain X
Now Compute these two metrics
Support and Confidence – 2nd Example
Transaction ID Items Bought
1001 A, B, C
1002 A, C
1003 A, D
1004 B, E, F
1005 A, D, F
Itemset {A, C} has a support of 2/5 = 40% Rule {A} ==> {C} has confidence of 50% Rule {C} ==> {A} has confidence of 100% Support for {A, C, E} ? Support for {A, D, F} ? Confidence for {A, D} ==> {F} ? Confidence for {A} ==> {D, F} ?
Goal: Find all rules that satisfy the user-specified minimum support (minsup) and minimum confidence (minconf).
Example
Transaction data Assume: minsup = 30% minconf = 80%
An example frequent itemset: {Chicken, Clothes, Milk} [sup = 3/7]
Rules from the itemset are partitions of the items Association rules from above itemset: Clothes Milk, Chicken [sup = 3/7, conf = 3/3]
… …
Clothes, Chicken Milk, [sup = 3/7, conf = 3/3]
15
t1: Beef, Chicken, Milk t2: Beef, Cheese t3: Cheese, Boots t4: Beef, Chicken, Cheese t5: Beef, Chicken, Clothes, Cheese, Milk t6: Chicken, Clothes, Milk t7: Chicken, Milk, Clothes
Mining Association Rules
TID Items
1 Bread, Milk
2 Bread, Diaper, Beer, Eggs
3 Milk, Diaper, Beer, Coke
4 Bread, Milk, Diaper, Beer
5 Bread, Milk, Diaper, Coke
Example of Rules:
{Milk,Diaper} {Beer} (s=0.4, c=0.67) {Milk,Beer} {Diaper} (s=0.4, c=1.0) {Diaper,Beer} {Milk} (s=0.4, c=0.67) {Beer} {Milk,Diaper} (s=0.4, c=0.67) {Diaper} {Milk,Beer} (s=0.4, c=0.5) {Milk} {Diaper,Beer} (s=0.4, c=0.5)
Observations:
• All the above rules are binary partitions of the same itemset: {Milk, Diaper, Beer}
• Rules originating from the same itemset have identical support (by definition) but may have different confidence values
Drawback of Confidence
Coffee
Coffee
Tea 15 5 20
Tea 75 5 80
90 10 100
Association Rule: Tea Coffee
Confidence= P(Coffee|Tea) = 0.75
but P(Coffee) = 0.9
Although confidence is high, rule is misleading
P(Coffee|Tea) = 0.9375
Mining Association Rules
Two-step approach:
1. Frequent Itemset Generation
– Generate all itemsets whose support minsup
2. Rule Generation – Generate high confidence rules from each frequent itemset,
where each rule is a binary partitioning of a frequent itemset
Frequent itemset generation is still computationally expensive
Transaction data representation
A simplistic view of “shopping baskets”
Some important information not considered:
the quantity of each item purchased
the price paid
19
Many mining algorithms
There are a large number of them
They use different strategies and data structures.
Their resulting sets of rules are all the same.
Given a transaction data set T, and a minimum support and a minimum confident, the set of association rules existing in T is uniquely determined.
Any algorithm should find the same set of rules although their computational efficiencies and memory requirements may be different.
We study only one: the Apriori Algorithm
20
The Apriori algorithm
The best known algorithm
Two steps:
Find all itemsets that have minimum support (frequent itemsets, also called large itemsets).
Use frequent itemsets to generate rules.
E.g., a frequent itemset {Chicken, Clothes, Milk} [sup = 3/7]
and one rule from the frequent itemset
Clothes Milk, Chicken [sup = 3/7, conf = 3/3]
21
Step 1: Mining all Frequent Itemsets
A frequent itemset is an itemset whose support is ≥ minsup.
Key idea: The Apriori property (downward closure property): any subsets of a frequent itemset are also frequent itemsets
22
AB AC AD BC BD CD
A B C D
ABC ABD ACD BCD
Steps in Association Rule Discovery
Find frequent itemsets
Itemsets with at least minimum support
Support is “downward closed” so a subset of a frequent itemset must be frequent if {AB} is a frequent itemset, both {A} and {B} are frequent itemsets
If an itemset doesnot satisfy minimum support, none of its supersets will either (this is key point that allows pruning of search space)
Iteratively find frequent itemsets with cardinality from 1 to k (k-itemsets)
Use the frequent itemsets to generate assoc. rules
Generate all binary partitions, but may have to fit template
E.g., only one item on right side or only two items on left side
Frequent Itemset Generation
24
null
AB AC AD AE BC BD BE CD CE DE
A B C D E
ABC ABD ABE ACD ACE ADE BCD BCE BDE CDE
ABCD ABCE ABDE ACDE BCDE
ABCDE
Given d items, there
are 2d possible
candidate itemsets
Mining Association Rules—An Example
For rule A C:
support = support({A ,C}) = 50%
confidence = support({A ,C})/support({A}) = 66.6%
The Apriori principle:
Any subset of a frequent itemset must be frequent
25
Transaction ID Items Bought
2000 A,B,C
1000 A,C
4000 A,D
5000 B,E,F
Frequent Itemset Support
{A} 75%
{B} 50%
{C} 50%
{A,C} 50%
Min. support 50%
Min. confidence 50%
User specifies these
26
Illustrating the Apriori Principle
Found to be
Infrequent
null
AB AC AD AE BC BD BE CD CE DE
A B C D E
ABC ABD ABE ACD ACE ADE BCD BCE BDE CDE
ABCD ABCE ABDE ACDE BCDE
ABCDE
null
AB AC AD AE BC BD BE CD CE DE
A B C D E
ABC ABD ABE ACD ACE ADE BCD BCE BDE CDE
ABCD ABCE ABDE ACDE BCDE
ABCDE
Pruned
supersets
The Apriori Algorithm
Terminology:
Ck is the set of candidate k-itemsets
Lk is the set of k-itemsets
Join Step: Ck is generated by joining two elements from Lk-1
There must be a lot of overlap for the join to only increase length by 1
Prune Step: Any (k-1)-itemset that is not frequent cannot be a subset of a frequent k-itemset
This is a bit confusing since we want to use it the other way. We prune a candidate k-itemset if any of its k-1 itemsets are not in our list of frequent k-1 itemsets
To utilize this you simply start with k=1, which is single-item itemsets and they you work your way up from there!
27
The Algorithm
Iterative algo. (also called level-wise search): Find all 1-item frequent itemsets; then all 2-item frequent itemsets, and so on.
In each iteration k, only consider itemsets that contain some k-1 frequent itemset.
Find frequent itemsets of size 1: F1
From k = 2 Ck = candidates of size k: those itemsets of size k that
could be frequent, given Fk-1
Fk = those itemsets that are actually frequent, Fk Ck (need to scan the database once).
28
Apriori Candidate Generation
The candidate-gen function takes Lk-1 and returns a superset (called the candidates) of the set of all frequent k-itemsets.
There are two steps: join step: Generate all possible candidate itemsets
Ck of length k
prune step: Remove those candidates in Ck that cannot be frequent.
29
How to Generate Candidates?
Suppose the items in Lk-1 are listed in an order
Step 1: self-joining Lk-1
The description below is a bit confusing– all we do is splice two sets
together so that only one new item is added (see next slide)
insert into Ck
select p.item1, p.item2, …, p.itemk-1, q.itemk-1
from Lk-1 p, Lk-1 q
where p.item1=q.item1, …, p.itemk-2=q.itemk-2, p.itemk-1 < q.itemk-1
Step 2: pruning
forall itemsets c in Ck do
forall (k-1)-subsets s of c do
if (s is not in Lk-1) then delete c from Ck
30
Self-Joining Step
All items in the itemset to be self joined are in a consistent order– any order
Such as lexicographic (alphabetical) order
Two items in the itemset can be joined only if they differ in the last position
Then when you join them the size of the itemset goes up by one
See example on next slide
31
Example of Generating Candidates (1)
L3={abc, abd, acd, ace, bcd}
Self-joining: L3*L3
abc and abd yields abcd
acd and ace yields acde
We do not join abd and acd
Even though it would give abcd which is a candidate
If the product were a candidate it would have already been generated given the ordering
This may not be obvious at first glance 32
Example of Generating Candidates (2)
Note that for abcd to be frequent by the Apriori property abc, bcd, and abd must be frequent
abc and abd are alphabetically before bcd
So if we see abc and bcd we do not need to generate abcd because if abd were there it would have already been generated
If it is not there then it would be pruned later
33
Example of Generating Candidates (3)
Given abde we go to the pruning phase
acde is removed because ade is not in L3
Merge step does not ensure all subsets are frequent
C4={abcd}
34
The Apriori Algorithm — Example (minsup = 30%)
35
TID Items
100 1 3 4
200 2 3 5
300 1 2 3 5
400 2 5
Database D itemset sup.
{1} 2
{2} 3
{3} 3
{4} 1
{5} 3
itemset sup.
{1} 2
{2} 3
{3} 3
{5} 3
Scan D
C1
L1
itemset
{1 2}
{1 3}
{1 5}
{2 3}
{2 5}
{3 5}
itemset sup
{1 2} 1
{1 3} 2
{1 5} 1
{2 3} 2
{2 5} 3
{3 5} 2
itemset sup
{1 3} 2
{2 3} 2
{2 5} 3
{3 5} 2
L2
C2 C2
Scan D
C3 L3 itemset
{2 3 5}Scan D itemset sup
{2 3 5} 2
Warning: Do Not Forget Pruning
Rules get pruned in two ways Apriori property violated If Apriori not violated, still must scan database and if
minsup not exceeded then prune Apriori property is necessary but not sufficient to keep a
rule
If you forget to prune via Apriori property, you will get same results since will catch on the scan But I will take off points on an exam. Make it clear when
prune using Apriori property (do not fill in count when crossing off)
Apriori property cannot be violated until k=3. Begins go get trickier at k=4 since more subsets to check
36
Step 2: Rules from Frequent Itemsets
Frequent itemsets association rules
One more step is needed
For each frequent itemset X,
For each proper nonempty subset A of X, Let B = X - A
A B is an association rule if
Confidence(A B) ≥ minconf,
support(A B) = support(AB) = support(X)
confidence(A B) = support(A B) / support(A)
37
Generating Rules: an Example
Suppose {2,3,4} is frequent, with sup=50% Proper nonempty subsets: {2,3}, {2,4}, {3,4}, {2}, {3}, {4}, with sup=50%,
50%, 75%, 75%, 75%, 75% respectively These generate these association rules:
2,3 4, confidence=100% 2,4 3, confidence=100% 3,4 2, confidence=67% 2 3,4, confidence=67% 3 2,4, confidence=67% 4 2,3, confidence=67% All rules have support = 50%
Then apply confidence threshold to identify strong rules Rules that meet the support and confidence requirements If confidence threshold is 80% we are left with 2 strong rules
38
Generating Rules: Summary
To recap, in order to obtain A B, we need to have support(A B) and support(A)
All the required information for confidence computation has already been recorded in itemset generation. No need to see the data T any more.
This step is not as time-consuming as frequent itemset generation Hint: I almost always ask this on the exam
39
On Apriori Algorithm
Seems to be very expensive
Level-wise search
K = the size of the largest itemset
It makes at most K passes over data
In practice, K is bounded (10).
The algorithm is very fast. Under some conditions, all rules can be found in linear time.
Scale up to large data sets
40
Granularity of items
One exception to the “ease” of applying association rules is selecting the granularity of the items.
Should you choose: diet coke?
coke product?
soft drink?
beverage?
Should you include more than one level of granularity? Some association finding techniques allow you to represent
hierarchies explicitly
Multiple-Level Association Rules
Items often form a hierarchy
Items at the lower level are expected to have lower support
Rules regarding itemsets at appropriate levels could be quite useful
Transaction database can be encoded based on dimensions and levels
Food
Milk Bread
Skim 2% Wheat White
Mining Multi-Level Associations
A top-down, progressive deepening
approach
First find high-level strong rules: milk bread [20%, 60%]
Then find their lower-level “weaker” rules: 2% milk wheat bread [6%, 50%]
Usually requires different thresholds at
different levels to find meaningful rules
lower support at lower levels
Interestingness Measurements
Objective measures
Two popular measurements:
Support
Confidence
Subjective measures (Silberschatz & Tuzhilin, KDD95)
A rule (pattern) is interesting if
it is unexpected (surprising to the user); and/or
actionable (the user can do something with it)
44
Criticism to Support and Confidence
Example 1:
Among 5000 students 3000 play basketball 3750 eat cereal 2000 both play basket ball and eat cereal
play basketball eat cereal [40%, 66.7%] is misleading because the overall percentage of students eating cereal is 75% which is higher than 66.7%.
play basketball not eat cereal [20%, 33.3%] is far more interesting, although with lower support and confidence
45
basketball not basketball sum(row)
cereal 2000 1750 3750
not cereal 1000 250 1250
sum(col.) 3000 2000 5000
Lift of A => B = P(B|A)/P(B)
and a rule is interesting if lift is
not near 1.0
What is the lift of this rule?
(1/3)/(1250/5000) = 1.33
Customer Number vs. Transaction ID
In the homework you may have a problem where there is a customer id for each transaction
You can be asked to do association analysis based on the customer id If this is so, you need to aggregate the transactions to the
customer level
If a customer has 3 transactions then you just create an itemset containing all of the items in the union of the 3 transactions
Note we will ignore the frequency of purchase
46
Virtual items
If you’re interested in including other possible variables, can create “virtual items”
gift-wrap, used-coupon, new-store, winter-holidays, bought-nothing,…
Associations: Pros and Cons
Pros
can quickly mine patterns describing business/customers/etc. without major effort in problem formulation
virtual items allow much flexibility
unparalleled tool for hypothesis generation
Cons
unfocused not clear exactly how to apply mined “knowledge”
only hypothesis generation
can produce many, many rules! may only be a few nuggets among them (or none)
Association Rules
Association rule types:
Actionable Rules – contain high-quality, actionable
information
Trivial Rules – information already well-known by
those familiar with the business
Inexplicable Rules – no explanation and do not
suggest action
Trivial and inexplicable rules occur most often