How to keep customers and increase profits using predictive analytics powered by Clementine

1
How to keep customers and increase profits using
predictive analytics powered by Clementine

• Peter Caron, Product Manager
• Greg Rodda, Systems Engineer

2
Todays Agenda

• SPSS overview
• Predictive Analytics Definition and Application
• Clementine for Predictive Analytics
• Demo
• Questions

3
Who is SPSS?

• Leadership
• Market leader in Predictive Analytics
• Focus on client Customer Data analysis and
  deployment
  
• Stability
• Founded in 1968
• 30 year heritage in analytic technologies
• Proven track record
• 250,000 customer organizations
• 209M in revenue FY2002
• Analytics standard
• 80 of Fortune 500 are SPSS customers
• 90 plus market share in Survey MR agency space

4
Predictive Analysis Defined

• Predictive analysis helps connect data to
  effective action by drawing reliable conclusions
  about current conditions and future events.
  
• Gareth Herschel, Research Director, Gartner
  Group
  

5
Predictive Analytics Platform
Attract
Actions
Grow
Retain
Outcomes
Attributes
Fraud
Business User
6
Predictive Analytics Platform
Market Research
Reporting
Data
Text Mining
Web Mining
Data Mining
7
Solve business problems

• Attract new customers more profitably
• Grow customer value by selling more
• Keep customers longer by targeting retention
  offers
  
• Reduce the costs of fraud, waste and abuse
• Minimize risk in security, healthcare and finance

8
Prediction in the Customer Life Cycle
Loyalty
Transaction
Target by profile/score Predict profit/valueSele
ct best approach
Retention
Conversion
Reactivation
Acquisition
Time
9
Prediction in Fraud and Risk
Identify the odd cases in normal behavior
Potential fraud, suspect transactions, unusual
payments, etc.
10
Other Examples

• Improving logistics by predicting failures
• Predicting offender behavior
• Institutional Research
• Segmenting and predicting Web site behavior
• Uncovering issues in call center notes
• Identifying relationships between actors and
  events in security-related text
  
• Predicting suspicious events in financial
  transactions to catch money launderers

11
Results

• A telecommunications company
• Saved more customers up to 80 more takes for
  retention offer
  
• Reduced the direct mail budget for same churner
  mailing by 60
  
• A government agency
• Reduced Medicare payment errors by 50
• A financial services company
• Reduced mailing costs by 80
• Opened the same number of accounts with greater
  loyalty
  
• A healthcare research center
• Improved diagnosis of tumors through better
  tissue classification
  
• A retail company
• Increased response rate on mailings 2
• Yielded 950K in ROI

12
Predictive AnalyticsPowered by Clementine

• Industry-leading workbench for data mining
• Comprehensive range of tools for all stages of
  the data mining process
  
• Pioneered visual approach for maximum
  productivity
  
• Multiple modeling techniques to predict customer
  behavior
  
• Leading technology for text mining and Web mining

13
Methodology for data mining

• Focus on business issues
• CRISP-DM
• Cross Industry Standard Process for Data Mining
  (CRISP-DM)
  
• Consortium of data miners from various industries
  manufacturing, marketing, and government
  
• User-centric interactive
• Full process
• Goal is to use results in your organization

14
Clementine Demo
15
Special offer for seminar attendees!

• Purchase Clementine by December 29th and receive
  20 off the Introduction to Clementine training
  class.
  
• To register or for more information call
  800-543-5815,
  
• or visit us at http//www.spss.com/training.

16
Question and Answer

• Sales sales_at_spss.com
• Clementine
• http//www.spss.com/clementine/