Business Intelligent

DATA MINING TOOLS AND
APPLICATIONS
Submitted By:-
Tanuj Goyal
Ankit Chourasia
Vinita Singhal

WHAT IS DATA MINING?
 Data mining is the process of analysing data from different
perspectives and summarizing it into useful information -
information that can be used to increase revenue, cuts costs, or
both.
 Data mining software is one of a number of analytical tools for
analysing data. It allows users to analyse data from many
different dimensions or angles, categorize it, and summarize the
relationships identified.
 Technically, data mining is the process of finding correlations or
patterns among dozens of fields in large relational databases.



FOR EXAMPLE :-
One Midwest grocery chain used the data mining capacity of
Oracle to analyse local buying patterns.
They discovered that when men bought diapers on Thursdays and Saturdays, they also
tended to buy beer.
Further analysis showed that these shoppers typically did their weekly grocery shopping on
Saturdays. On Thursdays, however, they only bought a few items. The retailer concluded
that they purchased the beer to have it available for the upcoming weekend. The grocery
chain could use this newly discovered information in various ways to increase revenue. For
example, they could move the beer display closer to the diaper display. And, they could
make sure beer and diapers were sold at full price on Thursdays.

DATA MINING TOOLS
 Artificial neural networks
 Decision trees
 Nearest neighbour method
 Rule induction
 Data visualization



ARTIFICIAL NEURAL NETWORKS
 Artificial neural networks are computational models that are capable
of machine learning and pattern recognition. They are usually presented as
systems of interconnected "neurons" that can compute values from inputs by
feeding information through the network.
 For example, in a neural network for handwriting recognition, a set of input
neurons may be activated by the pixels of an input image representing a letter or
digit. The activations of these neurons are then passed on, weighted and
transformed by some function determined by the network's designer, to other
neurons, etc., until finally an output neuron is activated that determines which
character was read.


DECISION TREES
 Tree-shaped structures that represent sets of decisions. These
decisions generate rules for the classification of a dataset. They
provide a set of rules that you can apply to a new (unclassified)
dataset to predict which records will have a given outcome.




7
Decision Trees for Credit Card
Insurance Database
age
Cr Ins
<=43
Male
>43
Female
Critical value of 43 is determined
by the algorithm
N 3,Y 0
Decision:No
Gender
N 0, Y 6
Decision: Yes
Yes
No
N 4, Y 1
Decision: No
Yes 2, No 0
Decision? Yes
Dependent Variable
Life Insurance Promotion
A Production Rule
from the Tree

IF (age<=43)&(Sex=Male)
&(Credit Card In = No)
THEN Life Insurance = No



NEAREST NEIGHBOUR METHOD
 It is a simple algorithm that stores all available or
historical cases and classifies or predicts new cases
based on a similarity measure. It uses old patterns to
predict the new ones.



RULE INDUCTION
 Rule induction is the extraction of useful if-then rules
from data based on statistical significance.
 The Diaper – Beer incident is an example of Rule
induction tool.


DATA VISUALIZATION
 The visual interpretation of complex relationships in
multidimensional data is done so that it is easy to
understand. Graphics, charts, tables etc. are used to
illustrate data relationships.





DATA MINING APPLICATIONS
 Market Analysis and Management
 Target marketing, Customer Relation Management, Cross Selling, Market Segmentation
 Risk Analysis and Management
 Banks assume a financial risk when they grant loans
 Risk models attempt to predict the probability of default or fail to pay back the borrowed amount
 Credit cards
 Insurance companies
 Fraud detection and management
 Other Applications
 Text mining (news group, email, documents) andWeb analysis.
 Intelligent query answering


12
MARKET ANALYSIS AND MANAGEMENT
 Where are the data sources for analysis?
 Credit card transactions, loyalty cards, discount coupons, customer complaint calls, plus (public)
lifestyle studies,clickstreams
 Customer profiling-segmentation
 Data mining can tell you what types of customers buy what products (clustering or classification)
 Target marketing
 Find clusters of “model” customers who share the same characteristics: interest, income level,
spending habits, etc.


13
MARKET ANALYSIS AND MANAGEMENT
 Effectiveness of sales campaigns
 Advertisements, coupons, discounts, bonuses
 Promote products and attract customers
 Can help improve profits
 Compare amount of sales and number of transactions
 During the sales period versus before or after the sales campaign
 Association analysis
 Which items are likely to be purchased together with the items on sale

14
MARKET ANALYSIS AND MANAGEMENT
 Customer retention Analysis of Customer loyalty
 Sequences of purchases of particular customers
 Goods purchased at different periods by the same customers can be grouped into
sequences
 Changes in customer consumption or loyalty
 Suggests adjustments on the pricing and variety of goods
 To retain old customers and attract new customers
 Cross-selling and up-selling
 Associations from sales records
 A customer who buy a PC is likely to buy a printer
 Purchase Recommendations



FRAUD DETECTION AND MANAGEMENT
 Applications
 Widely used in health care, retail, credit card services, telecommunications (phone card
fraud), etc.
 Approach
 Use historical data to build models of fraudulent behavior and use data mining to help
identify similar instances
 Examples
 Credit card transactions: The FALCON fraud assessment system by HNC Inc. to signal
possibly fraudulent credit card transactions
 Money Laundering: Detect suspicious money transactions (US Treasury's Financial Crimes
Enforcement Network)
 Detecting telephone fraud: ASPECT European Research Gr.
 Unsupervised clustering to detect fraud in mobile phone networks
 Telephone call model: destinationof the call, duration, time of day or week. Analyze patterns that deviate froman
expected norm.


FINANCIAL DATA ANALYSIS
 Financial data
 complete, reliable, high quality
 Loan payment prediction and customer credit policy analysis



17
LOAN PAYMENT PREDICTION AND
CUSTOMER CREDIT POLICY ANALYSIS
 Factors influencing loan payment performance
 Loan-to-value ratio
 Term of the loan
 Debt ratio (total monthly debt/total monthly income)
 Payment-to-income ratio
 Income level
 Education level
 Residence region
 Credit history
 Analyst may find that
 Payment-Income ratio is a dominant factor while education level and debt ratio are not

18
RISK MANAGEMENT AND INSURANCE
 Determine insurance rates
 Manage investment portfolios
 Differentiate between companies and/or individuals who are
good and poor credit risks
 Farmer`s Group discover a scenario:
 Someone who owns a sports car is not a higher accident risk
 Conditions: the sport car to be a second car and the family car to be a
station wagon or a sedan



19
DATA MINING FOR THE
TELECOMMUNICATION INDUSTRY
 Telecommunication data are multidimensional
 Calling-time
 Duration
 Location of caller
 Location of callee
 Type of call
 Used to Identify and Compare
 Data Traffic
 System Workload
 Resource Usage
 User Group Behavior
 Profit
 Fraudulent pattern analysis and identification of unusual patterns
 To achieve customer loyalty
 Characteristics of customers affecting line usage



OTHER APPLICATIONS

• Sports and Gaming
• Predicting outcome of football games
• Text Mining
• Spam detection
• Educational Data Mining
• Clustering students
• Design enterece exams, selection policies
• Human Resources
• How to select applicants