Download What is Data Mining? - Information System Department ITATS

DATA MINING
Introduction
[email protected]
Why Mine Data? Commercial Viewpoint
• Lots of data is being collected
and warehoused
• Web data, e-commerce
• 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)
2
Why Mine Data? Scientific Viewpoint
• Data collected and stored at
enormous speeds (GB/hour)
• remote sensors on a satellite
• telescopes scanning the skies
• microarrays 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
3
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
4,000,000
3,500,000
The Data Gap
3,000,000
2,500,000
2,000,000
1,500,000
Total new disk (TB) since 1995
1,000,000
Number of
analysts
500,000
0
1995
1996
1997
1998
1999
From:
R. Grossman, C. Kamath, V. Kumar, “Data Mining for Scientific and Engineering Applications”
4
What is Data Mining?
• Many Definitions
• 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
5
What is (not) Data Mining?
What is not Data
Mining?

6

What is Data Mining?
– Look up phone
number in phone
directory
– Certain names are more
prevalent in certain US
locations (O’Brien, O’Rurke,
O’Reilly… in Boston area)
– Query a Web
search engine for
information about
“Amazon”
– Group together similar
documents returned by
search engine according to
their context (e.g. Amazon
rainforest, Amazon.com,)
Query Examples
• Database
– Find all credit applicants with last name of Smith.
– Identify customers who have purchased more
than $10,000 in the last month.
– Find all customers who have purchased milk
• Data Mining
– Find all credit applicants who are poor credit
risks. (classification)
– Identify customers with similar buying habits.
(Clustering)
– Find all items which are frequently purchased
with milk. (association rules)
8
Applications
In finance, telecom, insurance and retail:
• Loan/credit card approval
• market segmentation
• fraud detection
• better marketing
• trend analysis
• market basket analysis
• customer churn
• Web site design and promotion
©GKGupta
9
Loan/Credit card approvals
In a modern society, a bank does not know its
customers. Only knowledge a bank has is their
information stored in the computer.
Credit agencies and banks collect a lot of customers’
behavioural data from many sources. This information is
used to predict the chances of a customer paying back a
loan.
©GKGupta
10
Market Segmentation
• Large amounts of data about customers contains
valuable information
• The market may be segmented into many subgroups
according to variables that are good discriminators
• Not always easy to find variables that will help in market
segmentation
©GKGupta
11
Fraud Detection
• Very challenging since it is difficult to define
characteristics of fraud. Often based on detecting
changes from the norm.
• In statistics, it is common to throw out the outliers but in
data mining it may be useful to identify them since they
could either be due to errors or perhaps fraud.
©GKGupta
12
Better Marketing
When customers buy new products, other products may
be suggested to them when they are ready.
As noted earlier, in mail order marketing for example, one
wants to know:
- will the customer respond?
- will the customer buy and how much?
- will the customer return purchase?
- will the customer pay for the purchase?
©GKGupta
13
Better Marketing
It has been reported that more than 1000 variable
values on each customer are held by some mail order
marketing companies.
The aim is to “lift” the response rate.
©GKGupta
14
Trend analysis
In a large company, not all trends are always visible to the
management. It is then useful to use data mining software
that will identify trends.
Trends may be long term trends, cyclic trends or seasonal
trends.
©GKGupta
15
Market Basket Analysis
• Aims to find what the customers buy and what they buy
together
• This may be useful in designing store layouts or in
deciding which items to put on sale
• Basket analysis can also be used for applications other
than just analysing what items customers buy together
©GKGupta
16
Customer Churn
• In businesses like telecommunications, companies are
trying very hard to keep their good customers and to
perhaps persuade good customers of their competitors to
switch to them.
• In such an environment, businesses want to find which
customers are good, why customers switch and what
makes customers loyal.
• Cheaper to develop a retention plan and retain an old
customer than to bring in a new customer.
©GKGupta
17
Customer Churn
• The aim is to get to know the customers better so you will
be able to keep them longer.
• Given the competitive nature of businesses, customers
will move if not looked after.
• Also, some businesses may wish to get rid of customers
that cost more than they are worth e.g. credit card
holders that don’t use the card, bank customers with very
small amount of money in their accounts.
©GKGupta
18
Web site design
• A Web site is effective only if the visitors easily find what
they are looking for.
• Data mining can help discover affinity of visitors to
pages and the site layout may be modified based on this
information.
©GKGupta
19
Data Mining Process
Successful data mining involves careful determining the
aims and selecting appropriate data.
The following steps should normally be followed:
1. Requirements analysis
2. Data selection and collection
3. Cleaning and preparing data
4. Data mining exploration and validation
5. Implementing, evaluating and monitoring
6. Results visualisation
©GKGupta
20
Requirements Analysis
The enterprise decision makers need to formulate goals
that the data mining process is expected to achieve. The
business problem must be clearly defined. One cannot
use data mining without a good idea of what kind of
outcomes the enterprise is looking for.
If objectives have been clearly defined, it is easier to
evaluate the results of the project.
©GKGupta
21
Data Selection and Collection
Find the best source databases for the data that is
required. If the enterprise has implemented a data
warehouse, then most of the data could be available
there. Otherwise source OLTP systems need to be
identified and required information extracted and stored
in some temporary system.
In some cases, only a sample of the data available may
be required.
©GKGupta
22
Cleaning and Preparing Data
This may not be an onerous task if a data warehouse
containing the required data exists, since most of this must
have already been done when data was loaded in the
warehouse.
Otherwise this task can be very resource intensive,
perhaps more than 50% of effort in a data mining project is
spent on this step. Essentially a data store that integrates
data from a number of databases may need to be created.
When integrating data, one often encounters problems like
identifying data, dealing with missing data, data conflicts
and ambiguity. An ETL (extraction, transformation and
loading) tool may be used to overcome these problems.
©GKGupta
23
Exploration and Validation
Assuming that the user has access to one or more data
mining tools, a data mining model may be constructed
based on the enterprise’s needs. It may be possible to
take a sample of data and apply a number of relevant
techniques. For each technique the results should be
evaluated and their significance interpreted.
This is likely to be an iterative process which should lead
to selection of one or more techniques that are suitable
for further exploration, testing and validation.
©GKGupta
24
Implementing, Evaluating and Monitoring
Once a model has been selected and validated, the
model can be implemented for use by the decision
makers. This may involve software development for
generating reports or for results visualisation and
explanation for managers.
If more than one technique is available for the given data
mining task, it is necessary to evaluate the results and
choose the best. This may involve checking the accuracy
and effectiveness of each technique.
©GKGupta
25
Implementing, Evaluating and Monitoring
Regular monitoring of the performance of the techniques
that have been implemented is required. Every enterprise
evolves with time and so must the data mining system.
Monitoring may from time to time to lead to the
refinement of tools and techniques that have been
implemented.
©GKGupta
26
Results Visualisation
Explaining the results of data mining to the decision
makers is an important step.
Most DM software includes data visualisation modules
which should be used in communicating data mining
results to the managers.
Clever data visualisation tools are being developed to
display results that deal with more than two dimensions.
The visualisation tools available should be tried and used
if found effective for the given problem.
©GKGupta
27
Data Mining Process – Another Approach
The last few slides presented one approach.
Another approach that also includes six steps has been
proposed by CRISP–DM (Cross–Industry Standard
Process for Data Mining) developed by an industry
consortium.
The six steps are:
1.
2.
3.
4.
5.
6.
Business understanding
Data understanding
Data preparation
Modelling
Evaluation
Deployment
©GKGupta
CRISP Data Mining Model
28
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
Statistics/
AI
Machine Learning/
Pattern
Recognition
Data Mining
Database
systems
29
Data Mining Tasks
• Prediction Methods
• Use some variables to predict unknown or future values of other
variables.
• Description Methods
• Find human-interpretable patterns that describe the data.
From [Fayyad, et.al.] Advances in Knowledge Discovery and Data Mining, 1996
30
Data Mining Models and Tasks
Data Mining Tasks...
• Classification [Predictive]
• Clustering [Descriptive]
• Association Rule Discovery [Descriptive]
• Sequential Pattern Discovery [Descriptive]
• Regression [Predictive]
• Deviation Detection [Predictive]
32
©GKGupta
33
Association Analysis
• Association analysis involves discovery of relationships
or correlations among a set of items.
• Discovering that personal loans are repaid with 80%
confidence when the person owns his home.
• The classical example is the one where a store
discovered that people buying nappies tend also to buy
beer.
©GKGupta
34
Associations
The association rules are often written as X → Y meaning
that whenever X appears Y also tends to appear. X and
Y may be collection of attributes.
A supermarket like Woolworths may have several
thousand items and many millions of transactions a week
(i.e. Gigabytes of data each week). Note that the
quantities of items bought is ignored.
©GKGupta
35
Classification and Prediction
A set of training objects each with a number of attribute
values are given to the classifier. The classifier formulates
rules for each class in the training set so that the rules
may be used to classify new objects. Some techniques do
not require training data.
Classification may be used for predicting the class label of
data objects. Number of techniques including decision
tree and neural network.
©GKGupta
36
Cluster Analysis
Similar to classification in that the aim is to build clusters
such that each of them is similar within itself but is
dissimilar to others. Clustering does not rely on classlabeled data objects.
Based on the principle of maximizing the intracluster
similarity and minimizing the intercluster similarity.
©GKGupta
37
Data Warehousing and OLAP
Data warehousing is a process by which an enterprise
collects data from the whole enterprise to build a single
version of the truth. This information is useful for decision
makers and may also be used for data mining. A data
warehouse can be of real help in data mining since data
cleaning and other problems of collecting data would have
already been overcome.
OLAP (Online Analytical Processing) tools are decision
support tools that are often built on top of a data
warehouse or another database. OLAP goes further than
traditional query and report tools in that a decision maker
already has a hypothesis which he/she is trying to test.
©GKGupta
38
Data Warehousing and OLAP
Data mining is somewhat different than OLAP since in
data mining a hypothesis is not being tested. Instead data
mining is used to uncover novel patterns in the data.
©GKGupta
39
Before Data Mining
To define a data mining task, one needs to answer the
following:
• What data set do I want to mine?
• What kind of knowledge do I want to mine?
• What background knowledge could be useful?
• How do I measure if the results are interesting?
• How do I display what I have discovered?
©GKGupta
40
Task-relevant Data
The whole database may not be required since it may be
that we only want to study something specific e.g. trends
in postgraduate students
- countries they come from
- degree program they are doing
- their age?
- time they take to finish the degree
- scholarship they have they been awarded
May need to build a database subset before data mining
can be done.
©GKGupta
41
Task-relevant Data
Data collection is non-trivial.
OLTP data is not useful since it is changing all the time. In
some cases, data from more than one database may be
needed.
©GKGupta
42
Preprocessing
• A data mining process would normally involve
preprocessing
• Often data mining applications use data warehousing
• One approach is to pre-mine the data, warehouse it, then
carry out data mining
• The process is usually iterative and can take years of
effort for a large project
©GKGupta
43
Data Preprocessing
• Preprocessing is very important although often
considered too mundane to be taken seriously
• Preprocessing may also be needed after the data
warehouse phase
• Data reduction may be needed to transform very high
dimensional data to a lower dimensional data
©GKGupta
Data Preprocessing
• Feature Selection
• Use sampling?
• Normalization
• Smoothing
• Dealing with duplicates, missing data
• Dealing with time-dependent data
44
©GKGupta
45
Measuring interest
Data mining process may generate many patterns. We
cannot look at all of them and so need some way to
separate uninteresting results from the interesting ones.
This may be based on simplicity of pattern, rule length, or
level of confidence.
©GKGupta
46
Visualization
We must be able to display results so that they are easy
to understand.
Display may be a graph, pie chart, tables etc. Some
displays are better than others for a given kind of
knowledge.
©GKGupta
47
Guidelines for Successful Data Mining
• The data must be available
• The data must be relevant, adequate and clean
• There must be a well-defined problem
• The problem should not be solvable by means of ordinary
query or OLAP tools
• The results must be actionable
©GKGupta
48
Data Mining Software
As noted earlier, a large variety of DM software is now
available.
Some more widely used software is:
• IBM - Intelligent Miner and more
• SAS - Enterprise Miner
• Silicon Graphics - MineSet
• Oracle - Thinking Machines - Darwin
• Angoss - knowledgeSEEKER
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.
50
Classification Example
Tid Refund Marital
Status
Taxable
Income Cheat
Refund Marital
Status
Taxable
Income Cheat
1
Yes
Single
125K
No
No
Single
75K
?
2
No
Married
100K
No
Yes
Married
50K
?
3
No
Single
70K
No
No
Married
150K
?
4
Yes
Married
120K
No
Yes
Divorced 90K
?
5
No
Divorced 95K
Yes
No
Single
40K
?
6
No
Married
No
No
Married
80K
?
60K
10
7
Yes
Divorced 220K
No
8
No
Single
85K
Yes
9
No
Married
75K
No
10
10
No
Single
90K
Yes
Training
Set
Learn
Classifier
Test
Set
Model
Classification: Application 1
• Direct Marketing
• Goal: Reduce cost of mailing by targeting a set of
consumers likely to buy a new cell-phone product.
• Approach:
• Use the data for a similar product introduced before.
• We know which customers decided to buy and which decided
otherwise. This {buy, don’t buy} decision forms the class
attribute.
• Collect various demographic, lifestyle, and company-interaction
related information about all such customers.
• Type of business, where they stay, how much they earn, etc.
• Use this information as input attributes to learn a classifier
model.
From [Berry & Linoff] Data Mining Techniques, 1997
52
Classification: Application 2
• Fraud Detection
• Goal: Predict fraudulent cases in credit card
transactions.
• Approach:
• Use credit card transactions and the information on its account-
holder as attributes.
• When does a customer buy, what does he buy, how often he pays on time,
etc
• Label past transactions as fraud or fair transactions. This forms
the class attribute.
• Learn a model for the class of the transactions.
• Use this model to detect fraud by observing credit card
transactions on an account.
53
Classification: Application 3
• Customer Attrition/Churn:
• Goal: To predict whether a customer is likely to be lost to a
competitor.
• Approach:
• Use detailed record of transactions with each of the past and present
customers, to find attributes.
• How often the customer calls, where he calls, what time-of-the day he calls most, his
financial status, marital status, etc.
• Label the customers as loyal or disloyal.
• Find a model for loyalty.
From [Berry & Linoff] Data Mining Techniques, 1997
54
Classification: Application 4
• Sky Survey Cataloging
• Goal: To predict class (star or galaxy) of sky objects,
especially visually faint ones, based on the telescopic
survey images (from Palomar Observatory).
• 3000 images with 23,040 x 23,040 pixels per image.
• Approach:
• Segment the image.
• Measure image attributes (features) - 40 of them per object.
• Model the class based on these features.
• Success Story: Could find 16 new high red-shift quasars, some
of the farthest objects that are difficult to find!
From [Fayyad, et.al.] Advances in Knowledge Discovery and Data Mining, 1996
55
Classifying Galaxies
Courtesy: http://aps.umn.edu
Early
Class:
• Stages of Formation
Attributes:
• Image features,
• Characteristics of light
waves received, etc.
Intermediate
Late
Data Size:
• 72 million stars, 20 million galaxies
• Object Catalog: 9 GB
• Image Database: 150 GB
Clustering Definition
• Given a set of data points, each having a set of attributes,
and a similarity measure among them, find clusters such
that
• Data points in one cluster are more similar to one another.
• Data points in separate clusters are less similar to one another.
• Similarity Measures:
• Euclidean Distance if attributes are continuous.
• Other Problem-specific Measures.
57
Illustrating Clustering
x Euclidean Distance Based Clustering in 3-D space.
Intracluster distances
are minimized
Intercluster distances
are maximized
Clustering: Application 1
• Market Segmentation:
• Goal: subdivide a market into distinct subsets of
customers where any subset may conceivably be
selected as a market target to be reached with a
distinct marketing mix.
• Approach:
• Collect different attributes of customers based on their
geographical and lifestyle related information.
• Find clusters of similar customers.
• Measure the clustering quality by observing buying patterns of
customers in same cluster vs. those from different clusters.
59
Clustering: Application 2
• Document Clustering:
• Goal: To find groups of documents that are similar to each other
based on the important terms appearing in them.
• Approach: To identify frequently occurring terms in each document.
Form a similarity measure based on the frequencies of different
terms. Use it to cluster.
• Gain: Information Retrieval can utilize the clusters to relate a new
document or search term to clustered documents.
60
Illustrating Document Clustering
• Clustering Points: 3204 Articles of Los Angeles Times.
• Similarity Measure: How many words are common in
these documents (after some word filtering).
Category
Total
Articles
Correctly
Placed
555
364
Foreign
341
260
National
273
36
Metro
943
746
Sports
738
573
Entertainment
354
278
Financial
61
Clustering of S&P 500 Stock Data
z Observe Stock Movements every day.
z Clustering points: Stock-{UP/DOWN}
z Similarity Measure: Two points are more similar if the events
described by them frequently happen together on the same day.
z We used association rules to quantify a similarity measure.
Discovered Clusters
1
2
3
4
Applied-Matl-DOW N,Bay-Net work-Down,3-COM-DOWN,
Cabletron-Sys-DOWN,CISCO-DOWN,HP-DOWN,
DSC-Co mm-DOW N,INTEL-DOWN,LSI-Logic-DOWN,
Micron-Tech-DOWN,Texas-Inst-Down,Tellabs-Inc-Down,
Natl-Semiconduct-DOWN,Oracl-DOWN,SGI-DOW N,
Sun-DOW N
Apple-Co mp-DOW N,Autodesk-DOWN,DEC-DOWN,
ADV-M icro-Device-DOWN,Andrew-Corp-DOWN,
Co mputer-Assoc-DOWN,Circuit-City-DOWN,
Co mpaq-DOWN, EM C-Corp-DOWN, Gen-Inst-DOWN,
Motorola-DOW N,Microsoft-DOWN,Scientific-Atl-DOWN
Fannie-Mae-DOWN,Fed-Ho me-Loan-DOW N,
MBNA-Corp -DOWN,Morgan-Stanley-DOWN
Baker-Hughes-UP,Dresser-Inds-UP,Halliburton-HLD-UP,
Louisiana-Land-UP,Phillips-Petro-UP,Unocal-UP,
Schlu mberger-UP
Industry Group
Technology1-DOWN
Technology2-DOWN
Financial-DOWN
Oil-UP
Association Rule Discovery: Definition
• Given a set of records each of which contain some
number of items from a given collection;
• Produce dependency rules which will predict
occurrence of an item based on occurrences of other
TID items.
Items
1
2
3
4
5
63
Bread, Coke, Milk
Beer, Bread
Beer, Coke, Diaper, Milk
Beer, Bread, Diaper, Milk
Coke, Diaper, Milk
Rules Discovered:
{Milk} --> {Coke}
{Diaper, Milk} --> {Beer}
Association Rule Discovery: Application 1
• Marketing and Sales Promotion:
• Let the rule discovered be
{Bagels, … } --> {Potato Chips}
• Potato Chips as consequent => Can be used to
determine what should be done to boost its sales.
• Bagels in the antecedent => Can be used to see which
products would be affected if the store discontinues
selling bagels.
• Bagels in antecedent and Potato chips in consequent
=> Can be used to see what products should be sold
with Bagels to promote sale of Potato chips!
64
Association Rule Discovery: Application 2
• Supermarket shelf management.
• Goal: To identify items that are bought together by sufficiently many
customers.
• Approach: Process the point-of-sale data collected with barcode
scanners to find dependencies among items.
• A classic rule -• If a customer buys diaper and milk, then he is very likely to buy beer.
• So, don’t be surprised if you find six-packs stacked next to diapers!
65
Association Rule Discovery: Application 3
• Inventory Management:
• Goal: A consumer appliance repair company wants to
anticipate the nature of repairs on its consumer
products and keep the service vehicles equipped with
right parts to reduce on number of visits to consumer
households.
• Approach: Process the data on tools and parts required
in previous repairs at different consumer locations and
discover the co-occurrence patterns.
66
Sequential Pattern Discovery: Definition
•
Given is a set of objects, with each object associated with its own timeline of events, find rules that predict strong sequential
dependencies among different events.
•
Rules are formed by first disovering patterns. Event occurrences in the patterns are governed by timing constraints.
(A B)
(A B)
<= xg
(C)
(D E)
(C)
(D E)
>ng
<= ms
67
<= ws
Sequential Pattern Discovery: Examples
• In telecommunications alarm logs,
• (Inverter_Problem Excessive_Line_Current)
(Rectifier_Alarm) --> (Fire_Alarm)
• In point-of-sale transaction sequences,
• Computer Bookstore:
(Intro_To_Visual_C) (C++_Primer) -->
(Perl_for_dummies,Tcl_Tk)
• Athletic Apparel Store:
(Shoes) (Racket, Racketball) --> (Sports_Jacket)
68
Regression
• Predict a value of a given continuous valued variable
based on the values of other variables, assuming a linear
or nonlinear model of dependency.
• Greatly studied in statistics, neural network fields.
• Examples:
• Predicting sales amounts of new product based on
advetising expenditure.
• Predicting wind velocities as a function of temperature,
humidity, air pressure, etc.
• Time series prediction of stock market indices.
69
Deviation/Anomaly Detection
• Detect significant deviations from normal behavior
• Applications:
• Credit Card Fraud Detection
• Network Intrusion
Detection
Typical network traffic at University level may reach over 100 million connections per day
70
Challenges of Data Mining
• Scalability
• Dimensionality
• Complex and Heterogeneous Data
• Data Quality
• Data Ownership and Distribution
• Privacy Preservation
• Streaming Data
71