Predictive Enrollment Management: Attracting the Best Applicants for Your Institution Sherri Sahs Sy

1
Predictive Enrollment Management Attracting the
Best Applicants for Your InstitutionSherri
SahsSystems Engineer, SPSS
2
Commonly Asked Questions

• 1. Will I be able to get copies of the slides
  after the event?
• 2. Is this web seminar being taped so I or others
  can view it after the fact?

3
Commonly Asked Questions

• 1. Will I be able to get copies of the slides
  after the event?
• 2. Is this web seminar being taped so I or others
  can view it after the fact?

Yes
Yes
www.spss.com/events
4
Part V in Five-Part Webinar Series
Part III Predictive Student RetentionIdentifying
and Retaining At-Risk Students with Enterprise
Technology Archived on SPSS.com
Part I Enterprise Feedback Management in Higher
Education Archived on SPSS.com
Part II Predictive Alumni DevelopmentMaximizing
Fundraising Programs Archived on SPSS.com
Part IV Predictive Institutional
PlanningDemonstrating continuous improvement to
meet accreditation standards Archived on SPSS.com
Part V Predictive Enrollment ManagementAttractin
g the Best Applicants for your Institution April
4th, 2007
www.spss.com/events/predictivestudent
5
SPSS in Higher Education since 1968
Enrollment Management

• Recruitment and acquisition
• Admissions

• Promotion and marketing mix

Student Retention

• Student segmentation
• Retention

• Student feedback and satisfaction
• Student services

Alumni Development

• Fundraising
• Promotion and marketing mix

• Campaign optimization
• Alumni feedback and satisfaction

Teaching, Research Learning

• Curriculum development
• Survey research
• Resource management
• Medical trails

• Testing standardization
• Course/Professor evaluation
• Institutional planning

6
SPSS Fundamentals

• Founded in 1968
• Publicly traded on NASDAQ Stock up 120 in 2005
• Over 1200 employees in 60 countries
• Market Leader in Predictive Analytics
• Coverage in independent publications such as
  Chronicle of Higher Education, Education
  Technology News, Education Technology, Journal of
  Educational Technology Systems, Technology
  Learning and more
• Proven track record with impressive customer base
• All 129 of the top U.S. colleges and universities
  (Americas Best Colleges 2005, U.S. News
  World Report)
• 80 percent of the 25 largest U.S. school
  districts (National Center for Education
  Statistics)
• 95 of FORTUNE 1000 companies
• Dozens of federal or national agencies and
  ministries around the world, including every US
  cabinet-level department Defense military
  branch
• AIR- Collaborative Educational Series
• Hundreds of provincial, state, county, city and
  borough government entities, including all 50 US
  states

7

• SPSS in Institutional Administration

8

• SPSS in Institutional Administration

9
Business Challenge for Institutions
The need to provide better campus decision
support systems with an integrated view of data
is critically important to campuses in order to
manage the complexities of our institutions in a
turbulent market environment. - Educause
Source Educause Core Data Service, Fiscal Year
2005 Summary Report, Brian L. Hawkins and Julia
A. Rudy, November 2006.

10
Predictive Analytics

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

11
Data Mining Applications in Higher Education
By Jing Luan, Ph.D. Vice Chancellor, Educational
Services and Planning San Mateo County Community
College District And Founder, Knowledge Discovery
Laboratory Formerly Chief Planning and Research
Officer, Cabrillo College
12
How does SPSS EFM solution fit into the
Enrollment Management equation?

• With EFM, you can answer questions such as
• What are the profiles of my best students who
  matriculate, persist, and thrive at my school?
• Which of my applicants fit these profiles and
  what combination of courses offered, college
  marketing, recruiter attention, financial aid,
  and other resources will do the best job of
  getting them to enroll?

13
How are these questions answered?
Collect Data
Report
Analyze
14
Scenario Enrollment Management

• Goal Increase enrollment of ideal students and
  spend less marketing dollars in the process.

15
Step 1 Collect Data to Determine Who Your Best
Students Are

• Potential data sources
• CIRP Incoming Freshman Survey
• National Study for Student Engagement (NSSE)
  Survey Freshman data
• Student Information System (SIS) Data
  demographics
• Student Satisfaction Surveys

Collect Data
16
Step 1 Collect Data to Determine Who Your Best
Students Are

• SPSS Applications available to do this
• SPSS Dimensions Suite
• SPSS Text Analysis for Surveys

Collect Data
17
Data at the Heart of thePredictive Institution
Text data Up to 40better predictions

• Attitudinal data
• - Opinions
• Preferences
• Needs
• Desires

• Interaction data
• - Offers
• Results
• Context
• Click streams
• Notes

Web data Up to 20better predictions
Attitudes Up to 30better predictions
Student Information Systems Marketing Attitudinal
Web Call-center Operational Course
Management Campus Card Data
360 View

• Behavioral data
• - Orders
• - Transactions
• Payment history
• Usage history

• Descriptive data
• Attributes
• Characteristics
• Self-declared info
• (Geo)demographics

18
Data Preparation
Natural Language Processing
19
Step 2 Analyze the Collected Data to Determine
Who Your Best Students Are

• SPSS Tools available for Solution (may be one or
  several)
• SPSS Family Base, Trends, Regression, Advanced
  Models, Categories, Tables, Complex Samples,
  Classification Trees
• SPSS Dimensions Suite
• SPSS Text Analysis for Surveys
• SPSS Clementine
• SPSS Predictive Marketing

Analyze
20
An ExampleRecruiting Students
Y means The Student Applied!
21
An ExampleNow Whats the Pattern?
22
An ExampleAnd Now?
23
An ExampleGetting Help from Data Mining
Discovery 63 of these prospects did respond to
our marketing efforts!
24
Cluster Analysis
25
Cluster Analysis
26
Cluster Analysis
27
Cluster Analysis
28
Visual Cluster Exploration
29
Step 3 Report on findings so they may be used in
further analyses/decision-making

• SPSS Tools available for Solution (may be one or
  several)
• Clementine Solution Publisher
• SPSS Tables
• SmartViewer Web Server
• SPSS Predictive Enterprise Services
• Integrate with existing ERP/CRM solutions

Report
30
Step 4 Collect Data to Determine Who Your Best
Applicants Are

• Potential data sources
• CIRP Incoming Freshman Survey Data
• NSSE Survey
• SIS Data
• Course Evaluations
• Student Satisfaction Surveys
• University Web Portal
• Text Data
• Web Behavior

Collect Data
31
Step 5 Analyze the Collected Data to Determine
Who Your Best Applicants Are and How to Attract
Them

• Devise framework of data models to identify those
  students best suited for institution
• Determine best mix of messaging and interactions
  to attract target applicants

Analyze
32
Data Understanding (visualization)
33
Combining Different Models
34
Measure Success with a Gains Chart

• This model compares two competing data mining
  models with a business rule

35
Why Bother?
16,000 fewer mailings with the same number of
conversions!
36
Lets do the numbers . . . .
37
Why predictive analytics?

• Understand who your best students are and
  optimize resources to attract more of these
  students
• Better collect and analyze information on
  prospects preferences, interests, and behaviors
• Combine this data with demographic information to
  customize your schools messages and interactions
  to an individuals needs
• Increase your success in converting a prospect or
  applicant to an enrolled student
• Ultimately Increase enrollments and spend less
  marketing dollars in the process.

38
Putting Data Mining into Production

• Asset Management
• Process Management

39
Analytical Asset Management
Analyst
40
Store Models Online
41
Why Organizations Choose SPSS

• Openness of System any data source/formats
• SOA well documented API in a web services
  environment ensures interoperability
• Leverage Database Power scalable for huge data
  sources
• Breadth and Use of Algorithms
• Learning Time domain data experts and
  Training
• Deployment into real-time production
• Methodology industry standard, CRISP-DM
• Cost Flexibility Academic, annual or
  perpetual, etc.
• SPSS Expertise over 35 years analytical
  experience

42
Gartner and Nucleus Research . . .

• Nucleus ResearchThe Real ROI from SPSS
• 94 of customers achieved a positive ROI, with an
  average payback period of 10.7 months
• Key benefits achieved include reduced costs,
  increased productivity, improved customer
  employee satisfaction, and greater visibility
  into operations
• 81 of projects deployed on time, 75 on or under
  budget

This is one of the highest ROI scores Nucleus
has ever seen in its Real ROI series of research
reports. Rebecca Wettemann, Vice President of
Research, Nucleus Research
Magic Quadrant
. . . vendors that offer the most relevant and
compelling solutions in the market.
43
ExampleAcademic Customers, worldwide
44
QA
Sherri Sahs SPSS Inc. 233 S. Wacker Drive, 11th
Floor, Chicago, IL 60606 P. 800.543.2185
extension 3427 e-mailssahs_at_spss.com website
www.spss.com