Temple University – CIS Dept.
CIS616– Principles of Data
Management
V. Megalooikonomou
Introduction to Data Mining
(based on notes by Jiawei Han and Micheline Kamber and on notes by Christos
Faloutsos)
General Overview - rel. model






Relational model - SQL
Functional Dependencies & Normalization
Physical Design; Indexing
Query processing/optimization
Transaction processing
Advanced topics



Distributed Databases
OO- and OR-DBMSs
Data Mining
Agenda

Motivation: Why data mining?

What is data mining?

Data Mining: On what kind of data?

Data mining functionality

Are all the patterns interesting?

Classification of data mining systems

Major issues in data mining
Motivation

Data rich but information poor!

Data explosion problem

Automated data collection tools and mature database technology
lead to tremendous amounts of data stored in databases, data
warehouses and other information repositories

Solution: Data Mining

Extraction of interesting knowledge (rules, regularities, patterns,
constraints) from data in large databases
Evolution of Database
Technology

1960s:


1970s:


Relational data model, relational DBMS implementation
1980s:


Data collection, database creation, IMS and network DBMS
RDBMS, advanced data models (extended-relational, OO,
deductive, etc.) and application-oriented DBMS (spatial, scientific,
engineering, etc.)
1990s—2000s:

Data mining and data warehousing, multimedia databases, and
Web databases
What Is Data Mining?

Data mining (knowledge discovery in databases):


Alternative names:


Extraction of interesting (non-trivial, implicit, previously
unknown and potentially useful) information or patterns
from data in large databases
Knowledge discovery(mining) in databases (KDD),
knowledge extraction, data/pattern analysis, data
archeology, information harvesting, business intelligence,
etc.
What is not data mining?


(Deductive) query processing.
Expert systems or small ML/statistical programs
What Is Data Mining?
• Now that we have gathered so much data,
what do we do with it?
• Extract interesting patterns (automatically)
•Associations (e.g., butter + bread --> milk)
• Sequences (e.g., temporal data related to stock market)
• Rules that partition the data (e.g., store location problem)
• What patterns are “interesting”?
information content, confidence and support,
unexpectedness, actionability (utility in decision making))
Why Data Mining? —
Potential Applications

Database analysis and decision support

Market analysis and management


Risk analysis and management



target marketing, market basket analysis,…
Forecasting, quality control, competitive analysis,…
Fraud detection and management
Other Applications

Text mining (newsgroup, email, documents) and Web analysis.

Spatial data mining

Intelligent query answering
Market Analysis and Management

Data sources for analysis? (Credit card transactions, discount
coupons, customer complaint calls, etc.)

Target marketing (Find clusters of “model” customers who share
same characteristics: interest, income level, spending habits, etc.)

Customer purchasing patterns over time (Conversion of
single to a joint bank account: marriage, etc.)

Cross-market analysis (Associations between product sales and
prediction based on associations)

Customer Profiling (What customers buy what products)

Customer Requirements (Best products for different customers)

Summary information (multidimensional summary reports)
Risk Analysis and
Management

Finance planning and asset evaluation



Resource planning:


cash flow analysis and prediction
cross-sectional and time series analysis (financialratio, trend analysis, etc.)
summarize and compare the resources and spending
Competition:



monitor competitors and market directions
group customers into classes and a class-based
pricing procedure
set pricing strategy in a highly competitive market
Fraud Detection and Management

Applications


Approach


health care, retail, credit card services, telecommunications etc.
use historical data to build models of normal and fraudulent behavior
and use data mining to help identify fraudulent instances
Examples




auto insurance: detect groups who stage accidents to collect insurance
money laundering: detect suspicious money transactions
medical insurance: detect professional patients and ring of doctors,
inappropriate medical treatment
detecting telephone fraud:Telephone call model: destination of the call,
duration, time of day/week. Analyze patterns that deviate from
expected norm.
Discovery of Medical/Biological
Knowledge

Discovery of structure-function associations




Human Brain Mapping (lesion-deficit, task-activation
associations)
Cell structure (cytoskeleton) and functionality or
pathology
Discovery of causal relationships


Structure of proteins and their function
Symptoms and medical conditions
DNA sequence analysis

Bioinformatics (microarrays, etc)
Other Applications

Sports


Astronomy


IBM Advanced Scout analyzed NBA game statistics (shots
blocked, assists, and fouls) to gain competitive advantage for
New York Knicks and Miami Heat
JPL and the Palomar Observatory discovered 22 quasars with
the help of data mining
Internet Web Surf-Aid

IBM Surf-Aid applies data mining algorithms to Web access logs
for market-related pages to discover customer preference and
behavior pages, analyzing effectiveness of Web marketing,
improving Web site organization, etc.
Data Mining: A KDD Process
Pattern Evaluation

Data mining: the core of
knowledge discovery
Data Mining
process.
Task-relevant Data
Data Warehouse
Data Cleaning
Data Integration
Databases
Selection
Steps of a KDD Process

Learning the application domain:




Creating a target data set: data selection
Data cleaning and preprocessing: (may take 60% of effort!)
Data reduction and transformation:




summarization, classification, regression, association, clustering.
Choosing the mining algorithm(s)
Data mining: search for patterns of interest
Pattern evaluation and knowledge presentation


Find useful features, dimensionality/variable reduction, invariant
representation.
Choosing functions of data mining


relevant prior knowledge and goals of application
visualization, transformation, removing redundant patterns, etc.
Use of discovered knowledge
Data Mining and Business
Intelligence
Increasing potential
to support
business decisions
Making
Decisions
Data Presentation
Visualization Techniques
Data Mining
Information Discovery
End User
Business
Analyst
Data
Analyst
Data Exploration
Statistical Analysis, Querying and Reporting
Data Warehouses / Data Marts
OLAP, MDA
Data Sources
Paper, Files, Information Providers, Database Systems
DBA
Architecture of a Typical Data
Mining System
Graphical user interface
Pattern evaluation
Data mining engine
Database or data
warehouse server
Data cleaning & data integration
Databases
Knowledge-base
Filtering
Data
Warehouse
Data Mining: On What Kind of
Data?




Relational databases
Data warehouses
Transactional databases
Advanced DB and information repositories







Object-oriented (OO)and object-relational (OR)
databases
Spatial databases (medical, satellite image DBs, GIS)
Temporal databases
Text databases
Multimedia databases (Image, Video, etc)
Heterogeneous and legacy databases
WWW
Data Mining Functionalities –
Patterns that can be mined

Concept description: Characterization and discrimination


Generalize, summarize, and contrast data characteristics, e.g.,
dry vs. wet regions
Association (correlation and causality)


Multi-dimensional vs. single-dimensional association
age(X, “20..29”) ^ income(X, “20..29K”)  buys(X, “PC”)
[support = 2%, confidence = 60%]

contains(T, “computer”)  contains(x, “software”) [1%, 75%]

Confidence(x  y) = P(y|x): degree of certainty of association

Support(x  y) = P(x y): % of transactions that the rule
satisfies
Data Mining Functionalities –
Patterns that can be mined

Classification and Prediction



Finding models (e.g., if-then rules, decision trees, mathematical
formulae, neural networks, classification rules) that describe and
distinguish classes or concepts for future prediction, e.g., classify
cars based on gasmileage
Prediction: Predict some unknown or missing numerical values
Cluster analysis


Class label is unknown: Group data to form new classes, e.g.,
cluster houses to find distribution patterns
Clustering principle: maximize intra-class similarity and minimize
interclass similarity
Data Mining Functionalities –
Patterns that can be mined

Outlier analysis

Outliers: data objects that do not comply with the general
behavior of the data (can be detected using statistical tests that
assume a prob. model)

Often considered as noise but useful in fraud detection, rare events
analysis

Trend and evolution analysis

Study regularities of objects whose behavior changes over time

Trend and deviation: regression analysis

Sequential pattern mining, periodicity analysis

Similarity-based analysis
When is a “Discovered” Pattern
Interesting?

A data mining system/query may generate thousands of patterns,
not all of them are interesting.


Suggested approach: Human-centered, query-based, focused mining
Interestingness measures: A pattern is interesting if it is
easily understood by humans, valid on new or test data with some
degree of certainty, potentially useful, novel, or validates some
hypothesis that a user seeks to confirm

Objective vs. subjective interestingness measures:

Objective: based on statistics and structures of patterns, e.g., support,
confidence, etc.

Subjective: based on user’s belief in the data, e.g., unexpectedness,
novelty, actionability, etc.
Can We Find All and Only
Interesting Patterns?


Find all the interesting patterns: Completeness

Can a data mining system find all the interesting patterns?

Association vs. classification vs. clustering
Search for only interesting patterns: Optimization

Can a data mining system find only the interesting patterns?

Approaches


First generate all the patterns and then filter out the uninteresting
ones
Generate only the interesting patterns—mining query optimization
Data Mining: Confluence of
Multiple Disciplines
Database
Technology
Machine
Learning
Information
Science
Statistics
Data Mining
Visualization
Other
Disciplines
Data Mining: Classification
Schemes


General functionality

Descriptive data mining

Predictive data mining
Different views, different classifications

Kinds of databases to be mined

Kinds of knowledge to be discovered

Kinds of techniques utilized

Kinds of applications adapted
A Multi-Dimensional View of Data
Mining Classification




Databases to be mined
 Relational, transactional, object-oriented, object-relational,
active, spatial, time-series, text, multi-media, heterogeneous,
legacy, WWW, etc.
Knowledge to be mined
 Characterization, discrimination, association, classification,
clustering, trend, deviation and outlier analysis, etc.
 Multiple/integrated functions and mining at multiple levels
Techniques utilized
 Database-oriented, data warehouse (OLAP), machine learning,
statistics, visualization, neural network, etc.
Applications adapted
 Retail, telecommunication, banking, fraud analysis, DNA mining,
stock market analysis, Web mining, Weblog analysis, etc.
Major Issues in Data Mining

Mining methodology and user interaction

Mining different kinds of knowledge in databases

Interactive mining of knowledge at multiple levels of abstraction


Incorporation of background knowledge to guide the discovery
process

Data mining query languages and ad-hoc data mining

Expression and visualization of data mining results

Handling noise and incomplete data

Pattern evaluation: the interestingness problem
Performance and scalability

Efficiency and scalability of data mining algorithms

Parallel, distributed and incremental mining methods
More details… Decision Trees

Decision trees





Problem
Approach
Classification through trees
Building phase - splitting policies
Pruning phase (to avoid over-fitting)
Decision Trees

Problem: Classification – i.e., given a training
set (N tuples, with M attributes, plus a label
attribute) find rules, to predict the label for
newcomers
Pictorially:
Decision trees
A ge
C hol-level G ender
30
150
M
…
C L A S S -ID
+
…
-
??
Decision trees

Issues:



missing values
noise
‘rare’ events
Decision trees

types of attributes



numerical (= continuous) - eg: ‘salary’
ordinal (= integer) - eg.: ‘# of children’
nominal (= categorical) - eg.: ‘car-type’
Decision trees

Pictorially, we have
num. attr#2
(e.g., chol-level)
+
+
+
+
+
+ +
-
- -
-
num. attr#1 (e.g., ‘age’)
Decision trees

and we want to label ‘?’
?
num. attr#2
(e.g., chol-level)
+
+
+
+
+
+ +
-
- -
-
num. attr#1 (e.g., ‘age’)
Decision trees

so we build a decision tree:
?
num. attr#2
(e.g., chol-level)
40
+
+
+
+
+
+ +
-
- -
-
50
num. attr#1 (e.g., ‘age’)
Decision trees

so we build a decision tree:
age<50
N
Y
+
Y
-
chol. <40
N
...
Decision trees

Typically, two steps:


tree building
tree pruning (for over-training/over-fitting)
Tree building

How?
num. attr#2
(e.g.,chol-level)
+ -+ +
+ + - - ++
num. attr#1 (e.g., ‘age’)
Tree building


How?
A: Partition, recursively - pseudocode:
Partition ( dataset S)
if all points in S have same label
then return
evaluate splits along each attribute A
pick best split, to divide S into S1 and S2
Partition(S1); Partition(S2)


Q1: how to introduce splits along attribute Ai
Q2: how to evaluate a split?
Tree building

Q1: how to introduce splits along attribute Ai

A1:

for numerical attributes:



binary split, or
multiple split
for categorical attributes:


compute all subsets (expensive!), or
use a greedy approach
Tree building


Q2: how to evaluate a split?
A: by how close to uniform each subset is
- ie., we need a measure of uniformity:
Tree building
Any other measure?
entropy: H(p+, p-)
p+: relative frequency of class + in S
1
0
0
0.5
1 p+
Tree building
‘gini’ index: 1-p+2 - p-2
entropy: H(p+, p-)
p+: relative frequency of class + in S
1
1
0
0
0
0.5
1 p+
0
0.5
1 p+
Tree building
Intuition:
 entropy: #bits to encode the class label
 gini: classification error, if we randomly
guess ‘+’ with prob. p+
Tree building
Thus, we choose the split that reduces
entropy/classification-error the most:
E.g.:
num. attr#2
(e.g., chol-level)
+ -+ +
++ + - - +
num. attr#1 (e.g., ‘age’)
Tree building

Before split: we need
(n+ + n-) * H( p+, p-) = (7+6) * H(7/13, 6/13)

bits total, to encode all the class labels
After the split we need:
0 bits
for the first
half and
(2+6) * H(2/8, 6/8) bits for the second
half
Tree pruning

What for?
num. attr#2
(eg., chol-level)
+ -+ +
++ + - - +
num. attr#1 (eg., ‘age’)
...
Tree pruning

Q: How to do it?
num. attr#2
(eg., chol-level)
+ -+ +
++ + - - +
num. attr#1 (eg., ‘age’)
...
Tree pruning


Q: How to do it?
A1: use a ‘training’ and a ‘testing’ set prune nodes that improve classification
in the ‘testing’ set. (Drawbacks?)
Tree pruning



Q: How to do it?
A1: use a ‘training’ and a ‘testing’ set prune nodes that improve classification
in the ‘testing’ set. (Drawbacks?)
A2: or, rely on MDL (= Minimum
Description Language) - in detail:
Tree pruning


envision the problem as compression
and try to minimize the # bits to
compress
(a) the class labels AND
(b) the representation of the decision tree
(MDL)


a brilliant idea – e.g.: best n-degree
polynomial to compress these points:
the one that minimizes (sum of errors + n )
Major Issues in Data Mining

Issues relating to the diversity of data types



Handling relational as well as complex types of data
Mining information from heterogeneous databases and global
information systems (WWW)
Issues related to applications and social impacts

Application of discovered knowledge





Domain-specific data mining tools
Intelligent query answering
Process control and decision making
Integration of the discovered knowledge with existing knowledge:
A knowledge fusion problem
Protection of data security, integrity, and privacy
Summary





Data mining: discovering interesting patterns from large amounts of
data
A natural evolution of database technology, in great demand, with
wide applications
A KDD process includes data cleaning, data integration, data
selection, transformation, data mining, pattern evaluation, and
knowledge presentation
Mining can be performed in a variety of information repositories
Data mining functionalities: characterization, discrimination,
association, classification, clustering, outlier and trend analysis, etc.

Classification of data mining systems

Major issues in data mining
Descargar

Dept. of CIS, Temple Univ. CIS661 – Principles of Data