Synetic College Logo
Unit 3 of 4 · M.Sc IT Sem 4

Unit 3: Data mining fundamentals

Data Warehousing and Data Mining notes · PTU syllabus (PGCA1941)

3 min read7 topics9 exam questions
On this page
  1. Unit summary
  2. Data mining and KDD
  3. Data mining functionalities
  4. Mining different kinds of data
  5. Classification vs clustering; predictive vs descriptive
  6. Market basket analysis
  7. Association rules and the Apriori algorithm
  8. Apriori worked example
  9. Key terms
  10. Quick revision
  11. Important questions

Unit summary

Data mining discovers useful patterns in large data sets. This unit covers data mining functionalities, kinds of data mined, classification vs clustering, predictive vs descriptive mining, association rule mining, market basket analysis and the Apriori algorithm.

After this unit you can

  • Describe data mining functionalities and the kinds of data mined
  • Distinguish classification and clustering, predictive and descriptive mining
  • Explain support, confidence and association rules
  • Apply the Apriori algorithm

PTU syllabus topics

  • Data mining functionalities
  • mining different kinds of data
  • classification vs clustering
  • predictive vs descriptive mining
  • association rule mining
  • market basket analysis
  • the Apriori algorithm
Key formulasAssociation rule measures

  • Support

    Count(A and B) / total transactions

  • Confidence

    Support(A and B) / Support(A)

  • Lift

    Confidence(A ⇒ B) / Support(B)

  • Apriori principle

    Subsets of frequent itemsets are frequent

1

Topic 1

Data mining and KDD

ProcessKnowledge discovery (KDD) process
  1. 1

    Data cleaning

  2. 2

    Data integration

  3. 3

    Data selection

  4. 4

    Data transformation

  5. 5

    Data mining

  6. 6

    Pattern evaluation

  7. 7

    Knowledge presentation

2

Topic 2

Data mining functionalities

Key termsFunctionalities
Characterisation and discrimination
Summarise a class; compare classes
Association
Items occurring together
Classification
Assign records to predefined classes
Prediction (regression)
Predict numeric values
Clustering
Group similar records without labels
Outlier analysis
Find unusual records (fraud)
Evolution analysis
Trends over time
3

Topic 3

Mining different kinds of data

Key termsKinds of data
Relational and warehouse data
Tables and cubes
Transactional
Market baskets
Time series and sequence
Stock prices, click streams
Spatial
Maps, GPS
Text and web
Documents, links, logs
Multimedia
Images, audio, video
Graph and social network
Connections between entities
4

Topic 4

Classification vs clustering; predictive vs descriptive

ComparisonClassification vs clustering
Classification
Clustering

Learning

Supervised — labelled training data

Unsupervised — no labels

Classes

Predefined

Discovered

Example

Spam or not spam

Customer segments

ComparisonPredictive vs descriptive mining
Predictive
Descriptive

Goal

Predict unknown or future values

Describe patterns in existing data

Techniques

Classification, regression, time-series forecasting

Clustering, association, summarisation

Example

Will this customer churn?

Which products sell together?

5

Topic 5

Market basket analysis

  • Market basket analysis studies customer transactions to find items bought together — used for shelf layout, cross-selling, bundles and recommendations ("customers who bought this also bought").
6

Topic 6

Association rules and the Apriori algorithm

An association rule X ⇒ Y means customers who buy X tend to buy Y (market basket analysis).

Key formulasRule measures

  • Support

    Transactions containing X and Y / total transactions

  • Confidence

    Support(X ∪ Y) / Support(X)

  • Lift

    Confidence / Support(Y)

    Lift > 1 means positive association

ProcessApriori algorithm
  1. 1

    Find frequent 1-itemsets

    Support ≥ minimum

  2. 2

    Join to form candidate k-itemsets

  3. 3

    Prune

    Drop candidates with an infrequent subset

  4. 4

    Count support and keep frequent ones

  5. 5

    Repeat until no new itemsets

  6. 6

    Generate rules with confidence ≥ minimum

Example

In 5 transactions, {bread, butter} appears in 3 and bread in 4: support = 60%, confidence(bread ⇒ butter) = 3/4 = 75%.

7

Topic 7

Apriori worked example

TIDItems
T1Bread, Milk
T2Bread, Butter, Eggs
T3Milk, Butter, Cola
T4Bread, Milk, Butter
T5Bread, Milk, Cola
  • Minimum support = 3 transactions (60%).
  • 1-itemsets: Bread 4, Milk 4, Butter 3, Cola 2, Eggs 1 → frequent: Bread, Milk, Butter.
  • 2-itemsets: {Bread, Milk} 3, {Bread, Butter} 2, {Milk, Butter} 2 → frequent: {Bread, Milk}.
  • Rules: Bread ⇒ Milk: confidence 3/4 = 75%; Milk ⇒ Bread: 3/4 = 75%.
  • Apriori property: every subset of a frequent itemset must be frequent — so any candidate with an infrequent subset is pruned. Limitations: many candidates and repeated database scans; FP-growth avoids candidate generation with an FP-tree.

Key terms

KDD
Knowledge discovery in databases
Support
Fraction of transactions containing an itemset
Confidence
P(B given A) for rule A → B
Frequent itemset
Itemset meeting minimum support
Apriori property
Every subset of a frequent itemset is frequent

Quick revision

  • KDD steps; functionalities; kinds of data.
  • Classification vs clustering; predictive vs descriptive.
  • Market basket, support, confidence, lift; Apriori join and prune.

Important exam questions

Practice questions written to the PTU exam pattern for this unit's syllabus: short answers (Section A style) and long answers (Sections B and C style).

Short-answer questions

  1. Q1.List the steps of KDD.
  2. Q2.Name four data mining functionalities.
  3. Q3.Distinguish classification and clustering.
  4. Q4.What is predictive mining?
  5. Q5.Define support and confidence.
  6. Q6.State the Apriori property.

Long-answer questions

  1. Q1.Explain data mining functionalities and the kinds of data mined.
  2. Q2.Distinguish predictive and descriptive mining, and classification and clustering.
  3. Q3.Explain the Apriori algorithm with an example.

Stuck on this unit?

Message SBS on WhatsApp for help with Data Warehousing and Data Mining, or to ask about studying M.Sc IT at Synetic.

WhatsApp us