You are on page 1of 9

8530521.doc Created by Chethan.

Data Mining
Goal of Data Mining
 Simplification and automation of the overall statistical process, from data source(s) to
model application
 Changed over the years
— Replace statistician ? Better models, less grunge work
— Many different data mining algorithms / tools available
— Statistical expertise required to compare different techniques
— Build intelligence into the software

Data Mining Is…


 Decision Trees
 Nearest Neighbor Classification
Neural Networks
 Rule Induction
 K-means Clustering

Data Mining is Not...


 Data warehousing
 SQL / Ad Hoc Queries / Reporting
 Software Agents
 Online Analytical Processing (OLAP)
 Data Visualization

Why data-mining now?


Data mining is an increasingly popular topic
(If the number of new textbooks is anything to go by).
Two main reasons:

 With computers now mediating most aspects of our lives, there has been a
large increase in the accumulation of electronic data.
 With computers being increasingly up to the demands of complex modeling, it
is getting easier to process larger datasets.

Why Mine Data? Commercial Viewpoint

 Data volumes are too large for classical analysis approaches:


 Large number of records
 High dimensional data
 Leverage organization’s data assets
 Only a small portion of the collected data is ever analyzed
 Data that may never be analyzed continues to be collected, at a great
expense, out of fear that something which may prove important in the
future is missing.

 Lots of data is being collected and warehoused


 Web data, e-commerce

ISiM
8530521.doc Created by Chethan.M

purchases at department/grocery stores


Bank/Credit Card transactions
 Computers have become cheaper and more powerful
 Competitive Pressure is Strong
 Provide better, customized services for an edge (e.g. In Customer
Relationship Management)

Scientific Viewpoint

 Data collected and stored at enormous speeds (GB/hour)

 remote sensors on a satellite


 telescopes scanning the skies
 micro arrays generating gene expression data
 scientific simulations generating terabytes of data

 Traditional techniques infeasible for raw data


 Data mining may help scientists

 In classifying and segmenting data


 In Hypothesis Formation

Origins of Data Mining


 Draws ideas from machine learning/AI, pattern recognition, statistics, and
database systems
 Traditional Techniques may be unsuitable due to
 Enormity of data
 High dimensionality of data
 Heterogeneous, distributed nature of data

Mining Large Data Sets - Motivation

 There is often information “hidden” in the data that is not readily evident
 Human analysts may take weeks to discover useful information
 Much of the data is never analyzed at all

What is Data Mining? ----- Many Definitions

 Data processing using sophisticated data search capabilities and statistical


algorithms to discover patterns and correlations in large preexisting databases; a
way to discover new meaning in data.
 Non-trivial extraction of implicit, previously unknown and potentially useful
information from data.
 Exploration & analysis, by automatic or semi-automatic means, of large quantities
of data in order to discover meaningful patterns.

ISiM
8530521.doc Created by Chethan.M

 The process of identifying commercially useful patterns or relationships in


databases or other computer repositories through the use of advanced statistical
tools.
 The automated extraction of predictive information from (large) databases.
 A step in the knowledge discovery process consisting of particular algorithms
(methods) that under some acceptable objective, produces a particular
enumeration of patterns (models) over the data.
 Data mining is the process of discovering interesting knowledge from large amounts
of data stored either in databases, data warehouses, or other information
repositories.

What is (not) Data Mining?


What is Data Mining?
What is not Data Mining?
Certain names are more prevalent in certain US
Look up phone number in phone
locations (O’Brien, O’Rurke, O’Reilly… in Boston
directory
area)
Query a Web search engine for
Group together similar documents returned by
information about “Amazon”
search engine according to their context (e.g.
Amazon rainforest, Amazon.com,)

ISiM
8530521.doc Created by Chethan.M

Statistics/AI Machine Learning/


Pattern Recognition

Data Mining

Database
systems

Data Mining Types:

 Predictive data mining: This produces the model of the system described by the
given data. It uses some variables or fields in the data set to predict unknown
or future values of other variables of interest.

 Descriptive data mining: This produces new, nontrivial information based on


the available data set. It focuses on finding patterns describing the data that
can be interpreted by humans.

Defining `data'
By `data', we mean sets of variable values, e.g.,

 Annual rainfall in Sussex for the last twenty years;


 Age, salary and IQ for all members of Sussex faculty.

Records
Values are organised in combinations called records.

Each record has a particular context, e.g., age, salary and IQ specifically for the
Informatics HoD.

Combinations may also be called vectors (esp. in neural-networks) and data-points


(esp. in statistics).

A single record is a datum.

ISiM
8530521.doc Created by Chethan.M

Tabulation
Data are often presented in a tabulated form, with one datum per row, and one
variable per column.
NAME AGE SALARY IQ

smith 42 36K 130


bloggs 29 30K 140
bush 50 60K 120
...
Where data are used for prediction, the to-be-predicted variable normally appears in
the final column (and is often called `class').

Basic data-types
Data may be classified according to the number and character of variables involved.

• Univariate/discrete: one variable with integer/symbolic values.


• Univariate/continuous: one variable with real/continuous values.
• Multivariate/discrete: more than one variable with integer/symbolic values.
• Multivariate/continuous: more than one variable with real/continuous values.

Data Mining Tasks...

 Classification [Predictive]
 Clustering [Descriptive]
 Association Rule Discovery [Descriptive]
 Sequential Pattern Discovery [Descriptive]
 Regression [Predictive]
 Deviation Detection [Predictive]

ISiM
8530521.doc Created by Chethan.M

Classification: Definition

 Given a collection of records (training set )

 Each record contains a set of attributes, one of the attributes is the class.

 Find a model for class attribute as a function of the values of other attributes.
 Goal: previously unseen records should be assigned a class as accurately as
possible.

 A test set is used to determine the accuracy of the model. Usually, the given
data set is divided into training and test sets, with training set used to build
the model and test set used to validate it.

Explicit and implicit structure


A dataset is a body of data.
Any dataset has explicit structure, ie., the numbers/values in the records.
Generally, there is also implicit structure.

Data mining is the task of identifying and modeling implicit structure, either as an end
in itself or as a means of obtaining new information.

Example: A-level grades


Dataset containing average A-level grades for the past ten years.

Explicit structure is the mapping between years and average grades.

(Explicit structure = `what you see')

ISiM
8530521.doc Created by Chethan.M

There is also implicit structure---a gradual increase in values over time. (Average
grades are increasing by approx 3% per year.)

Classification Example

al ous
ic al nu
or ic ti as
s
te
g r n cl Refund Marital Taxable
ca go co
Tid Refund te
Marital Taxable Status Income Cheat
Ca
Status Income Cheat
No Single 75K ?
1 Yes Single 125K No
Yes Married 50K ?
2 No Married 100K No
No Married 150K ?
3 No Single 70K No
Yes Divorced 90K ?
4 Yes Married 120K No
No Single 40K ?
5 No Divorced 95K Yes
No Married 80K ?
6 No Married 60K No
10

7 Yes Divorced 220K No


8 No Single 85K Yes
9 No Married 75K No Training Test
10 No Single 90K Yes Set Set

Learn
10

Classifier

Model

Challenges of Data Mining

 Scalability
 Dimensionality
 Complex and Heterogeneous Data
 Data Quality
 Data Ownership and Distribution
 Privacy Preservation
 Streaming Data

ISiM
8530521.doc Created by Chethan.M

 Statistical methods
 Case-based reasoning
 Neural networks
 Decision trees

DM & DW:
Data Warehousing + Data Mining = Increased performance of decision making
process + Knowledgeable decision makers

Data Mining Applications


 Data Mining For Financial Data Analysis
 Data Mining For Telecommunications Industry
 Data Mining For The Retail Industry
 Data Mining In Healthcare and Biomedical Research
 Data Mining In Science and Engineering

Reference:

ISiM
8530521.doc Created by Chethan.M

1. Introduction to Data Mining by Tan, Steinbach, Kumar


Data Mining: Concepts and Techniques

2. Data Mining: Concepts and Techniques: Jiawei Han and Micheline Kamber
3. Kurt Thearling, Ph.D. An Introduction to Data Mining. www.thearling.com

ISiM

You might also like