Scribd
Upload
13 views3 pages

Association Analysis Model Explained

The document outlines the mathematical model for association analysis, a data mining technique used to identify relationships among items in transactional databases. It defines key concepts such as itemsets, transactions, support, confidence, and lift, and explains the process of identifying large item sets based on a minimum support threshold. Additionally, it demonstrates how to generate association rules from these large item sets using a sample dataset.

Uploaded by

Siddharth Patni
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
13 views3 pages

Association Analysis Model Explained

The document outlines the mathematical model for association analysis, a data mining technique used to identify relationships among items in transactional databases. It defines key concepts such as itemsets, transactions, support, confidence, and lift, and explains the process of identifying large item sets based on a minimum support threshold. Additionally, it demonstrates how to generate association rules from these large item sets using a sample dataset.

Uploaded by

Siddharth Patni
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Mathematical Model for Association Analysis

Association analysis (or association rule mining) is a data mining technique to discover
interesting relations (associations, correlations) among a large set of items in transactional
databases.
Basic Concepts
1. Itemset
o A collection of one or more items.

o Example: {Milk, Bread} is a 2-itemset.

2. Transaction (T)
o A set of items bought together.

o Example: T1 = {Milk, Bread, Butter}

3. Support (Sup)
o Fraction of transactions that contain an itemset.

o Formula:
Number of transactions containing X
Support( X )=
Total number of transactions

4. Confidence (Conf)
o Strength of the rule X → Y (probability of Y given X).

o Formula:

Support ( X ∪ Y )
Confidence( X → Y )=
Support (X )

5. Lift
o Measures how much more likely X and Y occur together than expected if
independent.
o Formula:

Support( X ∪ Y )
Lift ( X →Y )=
Support ( X)× Support (Y )

Large Item Sets


Definition
 Large item sets (frequent item sets) are those itemsets whose support is greater
than or equal to a minimum support threshold.
 These are crucial because only large item sets are used to generate strong association
rules.
Example Dataset

Transaction ID Items

T1 {Milk, Bread, Butter}

T2 {Milk, Bread}

T3 {Bread, Butter}

T4 {Milk, Bread, Butter, Eggs}

T5 {Milk, Eggs}

Step 1: 1-Itemsets with Support


 Milk: appears in T1, T2, T4, T5 → Support = 4/5 = 0.8
 Bread: appears in T1, T2, T3, T4 → Support = 4/5 = 0.8
 Butter: appears in T1, T3, T4 → Support = 3/5 = 0.6
 Eggs: appears in T4, T5 → Support = 2/5 = 0.4
If min support = 0.5, then {Milk}, {Bread}, {Butter} are large item sets. {Eggs} is not.

Step 2: 2-Itemsets with Support


 {Milk, Bread}: in T1, T2, T4 → Support = 3/5 = 0.6
 {Milk, Butter}: in T1, T4 → Support = 2/5 = 0.4 (below threshold)
 {Bread, Butter}: in T1, T3, T4 → Support = 3/5 = 0.6
 {Milk, Eggs}: in T4, T5 → Support = 2/5 = 0.4
So large 2-itemsets: {Milk, Bread}, {Bread, Butter}

Step 3: 3-Itemsets with Support


 {Milk, Bread, Butter}: in T1, T4 → Support = 2/5 = 0.4 ❌

 No 3-itemset is frequent (under threshold).


Final Large Item Sets
 1-itemsets: {Milk}, {Bread}, {Butter}
 2-itemsets: {Milk, Bread}, {Bread, Butter}

Generating Rules from Large Item Sets


From {Milk, Bread} (Support = 0.6):
 Rule: Milk → Bread
Confidence = 0.6 / 0.8 = 0.75
 Rule: Bread → Milk
Confidence = 0.6 / 0.8 = 0.75
From {Bread, Butter} (Support = 0.6):
 Rule: Bread → Butter
Confidence = 0.6 / 0.8 = 0.75
 Rule: Butter → Bread
Confidence = 0.6 / 0.6 = 1.0 (strong rule)

You might also like