Jerry%20Held

1
Open World 2003
2
Data Warehousing for the Communications
Industry A Data Mining Approach to
Customer Churn Analysis in Wireless Industry
Session id 40332       

• Shyam Varan NathSenior Database Engineer
• Daleen Technologies

3
Introduction

• Oracle Data Mining
• JDeveloper
• DM4J
• Wireless Industry and Customer Churn
• Data Modeling for Churn Management

4
WLNP Threatens to Significantly Impact Wireless
Churn Rates.
Source In-Stat 2002
5
Churn
North American Wireless industry monthly churn
rate in Q4-02
2.8
2.4
Canadian Average
U.S. Average
Monthly Churn () - 4Q-02

• Source Company analyst reports

6
Wireless Industry Some Facts

• Wireless Local Number Portability (WLNP) from Nov
  2003
• Average Cost to Acquire a New Wireless Customer
  400 to 500
• Data Mining as a Solution to the Business Problem

7
facts
Source Duke Teradata 2002
8
facts
9
Reasons for Churn

• Many companies to choose from
• Similarity of their Offerings
• Cheap prices of the handsets
• The biggest current barrier to churn
• the lack of phone number portability!

10
A Dilemma

• Cross-Selling Through Database Marketing
• cross-selling is effective for customer retention
  by increasing switching costs and enhancing
  customer loyalty
• on the other hand, cross-selling can also
  potentially weaken the firms relationship with
  the customer, because frequent attempts to
  cross-sell can render the customer non-responsive
  or even motivated to switch to a competitor

11
Role of Data Mining

• Business Issues in a Wireless Industry

12
Some Definitions

• Data Warehousing Data warehousing is a database
  or a collection of databases designed to give
  business decision-makers instant access to
  information
• Data Mining The Data Mining is the process of
  using raw data to infer important business
  relationships that can then be used for business
  advantage

13

• Simply put, data mining is used to discover
  hidden patterns and relationships in your data
  in order to help you make better business
  decisions.

Source Oracle9i Data Mining 2001
14
Choice of Tools
15
Justification for Data Mining

• Reporting Tools Good at drilldowns into the
  details
• OLAP/Statistical Tools Used to draw conclusions
  from representative samples
• Data Mining Goes deep into the data. It uses
  machine-learning algorithms to automatically sift
  through each record and variable to uncover
  patterns and information that may have been
  hidden.

16
Predictive Modeling
Visual Representation of Predictive Modeling
17
Benefits Of Data Warehousing And Predictive
Modeling

• Immediate Information Delivery
• Data Integration from acrossand even outsidethe
  Organization
• Future Vision from Historical Trends
• Tools for Looking at Data in New Ways

18
What is ODM?
Connected to Oracle9i Enterprise Edition Release
9.2.0.1.0 - Production With the Partitioning,
OLAP and Oracle Data Mining options JServer
Release 9.2.0.1.0 - Production SQLgt Oracle9i Data
Mining, an option to Oracle9i Enterprise Edition,
that allows users to build advanced business
intelligence applications that mine corporate
databases to discover new insights, and integrate
those insights into business applications.
19
Why Oracle?
Integrated Environment of Oracle Relational
Database
20
Supervised v/s Unsupervised Learning

• Supervised learning requires identification of a
  target field or dependent variable. The
  supervised-learning technique then sifts through
  data trying to find patterns and relationships
  between the independent variables and the
  dependent variable. (ODM provides the Naïve Bayes
  data mining algorithm for supervised-learning
  problems.)
• Unsupervised learning allows the user not to
  indicate the objective to the data mining
  algorithm. Associations and clustering algorithms
  make no assumptions about the target field.
  Instead, try to find associations and clusters in
  the data independent of any a priori defined
  business objective Market-basket analysis etc.
  (ODM provides the Association Rules data mining
  algorithm for unsupervised-learning problems.)

21
Naive Bayes algorithm

• The Naive Bayes algorithm uses the mathematics of
  Bayes' Theorem to make its predictions. The
  algorithm is typically used for
• Identifying which customers are likely to
  purchase a certain product
• Identifying customers who are likely to churn
• Predicting the likelihood that a part will be
  defective
• Adaptive Bayes Network
• Human readable rules

IF RELATIONSHIP "Husband" AND EDUCATION_NUM
"13-16" THEN CHURN "TRUE"
22
Bayes Theorem
According to the Bayesian rule, the probability
of an example E being in class c is P(C ca1,
a2 , an) p(a1, a2 , anC c) p(C c)

p(a1, a2 , an)   The classification is taken as
the Cs value with the largest
probability Assume all attributes are
independent given the class p(a1, a2 , anc)
p(a1c) p (a2c) .p(anc) The resulting
Bayesian classifier is called the Naïve Bayesian
classifier.
23
Major Steps Of Data Mining

• Build Model Models are built in the data-mining
  server
• Test Model Model testing gives an estimate of
  model accuracy
• Compute Lift ODM supports computing lift for a
  binary classification model (confidence of
  prediction)
• Apply Model Applying a supervised learning model
  to data results in scores or predictions with an
  associated probability
• computing lift for a binary classification
  model,

24
Build Model
25
Apply Process
26
Data For Modeling
Nature of Dataset Used for Study (real Wireless
Customer Data)
27
System Setup

• Database
• Java Environment
• Data Mining Wizard

28
Database Oracle 9.2.0.1.0
Installation of Oracle Database Software
9.2.0.1.0 with Oracle Data Mining Option, with
the database patch for version 9.2.0.2.1 .
29
Java Environment JDeveloper
Installation of JDeveloper 9.0.3
30
Data Mining Wizard DM4J
31
Question
32
Getting Started

• Unlock odm user
• Grants on the tables for wizard to display
• Odm_mtr schema

33
Working with the DM4J Wizard
Creating a new Workspace
Configuring a Database Connection
34
DM4J
Selecting a model type in the DM4J wizard.
35
Algorithm for Data Modeling
Selecting the Algorithm
Fine tuning the algorithm
36
DM4J
The DM4J wizard generates the Java code that is
compiled and executed to create the model.
37
DM4J
Here is the Java Code!
38
Our Study
The input data was stored in a table called
CALIBRATION.
Our target variable for prediction is CHURN.
39
study
We pick all the input predictor variables (except
customer Id) from the list of 171 to predict
churn.
40
study
compilation and execution of the Java code
containing the ODM model.
The program runs in an asynchronous mode and we
can monitor the progress of the task. The screen
shot shows the successful completion of the
model.
41
study
The Adaptive Bayes Network also generates the
rules for the model in human readable form.
42
study
Confusion Matrix
Testing the Model using the data from table
PRESENT
Cumulative Lift Chart
43
study
The last step is to apply the tested model to the
data set where we want to predict the CHURN
44
study
After the Apply task is run
When we apply the model, the predictions are
obtained and stored in an output table
45
study
Rating the importance of the various predictor
variables.
46
Top Ten Variables

• DUALBAND type of phone set
• CARTYPE dominant vehicle lifestyle
• EDUC1 education level of first house hold member
• ETHNIC ethnicity
• TOT_ACPT total offers accepted from retention
  team
• OCCU1 occupation of the first household member
• AREA geographic area
• INCOME estimated household income
• DWLLSIZE dwelling size
• PROPTYPE property type details

47
Cost Savings Based on Churn Data
savings per churnable subscriber net(no
intervention) net(incentive) / L NL
net(no intervention) L NL X Cl
net(incentive) L LS Ci Pi L NL
Cl
To estimate cost savings, the parameters Ci (cost
of incentive per customer), Pi (reduction in
probability to churn due to incentive Ci), and Cl
(lost-revenue cost when a subscriber churns) are
combined with four statistics obtained from a
predictor model L number of subscribers who
are predicted to leave (churn) and who actually
leave barring Intervention. NL number of
subscribers who are predicted to stay (nonchurn)
and who actually leave barring Intervention. LS
number of subscribers who are predicted to leave
and who actually stay SS number of subscribers
who are predicted to stay and who actually stay
48
Churn Management
Expected Saving to Carrier / Churnable Subscriber
Source Mozer 2000
49
Future Trends and Conclusion

• Real time Analytics and Text Mining (Oracle 10G)
  can take Data Mining to next level.
• Oracle Data Mining can resolve a Business
  problem.
• Churn Prediction and Churn Management can yield
  significant savings to the wireless provider.

50
Daleen at a Glance

• Founded in 1989 with a mission to build custom
  software for finance telecom sectors
• Worldwide base of over 80 billing customer care
  contracts since 1997
• Innovator in deployment of convergent billing,
  event management revenue assurance solutions
  for next-generation services
• Long term focus on delivering exceptional
  customer service through a site license or
  service bureau relationship
• Offices in Boca Raton, St. Louis, Amsterdam
  Sydney

51
A
52
References Useful Links

• Technet http//technet.oracle.com/products/bi/odm/
  9idm4j
• Armstrong, G., and P. Kotler. 2001. Principles of
  Marketing. Prentice Hall New Jersey.
• Duke Teradata 2002. Teradata Center for Customer
  Relationship Management. On-line. Retrieved on
  Nov 7, 2002. Availablehttp//www.teradataduke.org
  /news_t_2.html
• In-Stat. 2002. WLNP Threatens to significantly
  impact wireless churn rates. Online. Retrieved
  on Sep 2002.
• Available http//www.instat.com/newmk.asp?ID312
  
• Mozer, Michael, Richard Wolniewicz, Eric Johnson
  and Howard Kaushansky. 1999. Churn
  reduction in the wireless industry, Proceedings
  of the Neural Information Processing Systems
  Conference, San Diego, CA.
• Oracle9i Data Mining 2001. An Oracle white paper
  December 2001. Online.
• Retrieved on Nov 8, 2002.
• Available http//otn.oracle.com/products/bi/pdf/
  o9idm_bwp.pdf) 
• Skedd, Kirsten 2002. WLNP threatens to
  significantly impact wireless churn rates
  On-line. Retrieved on Sep 14, 2002.
• Available http//www.instat.com/press.asp?ID311
  skuIN020258WP

53
Acknowledgements

• Dr Ravi Behara, Faculty (Florida Atlantic
  University)
• David Eastlund and Jennifer from Oracle
• Cohorts at Daleen Technologies

54
Reminder Please complete the OracleWorld
online session survey.Session id 40332 Data
Warehousing for the Communications Industry
Thank you.
55
Contact Information

• Email snath_at_daleen.com
• Cell Phone [phone]
• Test Message 9546092402_at_mobile.att.net

56
(No Transcript)