Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Predictive Analytics for Student Retention Webinar

No description
by

Cailean Hargrave

on 27 April 2015

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Predictive Analytics for Student Retention Webinar

PREDICTIVE ANALYTICS FOR STUDENT RETENTION
The Journey
- Business Workshops
- Cultural Adoption
- Holistic Approach
TECHNOLOGICAL TRANSFORMATION
AP
DM
SC
PA
CORE TEAM
EXECUTIVE TEAM
CHAMPION
NETWORK
EARLY
ADOPTERS
ITERATIVE DEVELOPMENT
CULTURAL TRANSFORMATION
ADOPTION
The Challenges
- Complexity of Environment
- Sticking to the Plan/Timescale
- Executing Benefit Realisation
The Benefits
- Increased Student Progression
- Greater Corporate Agility
- Transforming Teaching & Learning
Speakers
11.05 - 11.15 -
The Need to be Smarter

Cailean Hargrave - IBM UK Education Lead
11.15 - 11.25 -
Student Retention Solution
Marios Hajipavlou - IBM UK Edu Predictive Analytics
11.25 - 11.40 -
Predictive Analytics in Action
Dusan Magula - IBM UK Predictive Technical
11.40 - 11.50 -
Case Study - London South Bank Uni
David Swayne - LSBU Chief Information Officer
11.50 - 11.55 -
Education Sector Best Practice
Cailean Hargrave - IBM UK Education Lead
11.55 - 12.00 -
Questions and Answers
Cailean Hargrave - IBM UK Education Lead
CAILEAN HARGRAVE
IBM UK Education Lead
MARIOS HAJIPAVLOU
IBM UK Edu Predictive Analytics
DUSAN MAGULA
IBM UK Predictive Technical
DAVID SWAYNE
LSBU Chief Information Officer
Agenda
27,000
University students drop out in a year
The Telegraph
20%
Higher Education
“Over the past five years, in England alone, over
Sally Hunt, the UCU general secretary
15%
Further Education

National Audit Office
UK Dropout Rates
£1bn
has been spent on measures to improve
student retention in higher education,”
The Need to be Smarter
The Challenges Education Institutes Face
"Predictive Analytics helps connect data to effective action by drawing reliable conclusions about current conditions and future events"

Gareth Herschel, Research Director, Gartner Group

What is Predictive Analytics?
Student Retention Solution
Enrolment and Admissions
Student Retention
Student Experience
Teaching & Content Effectiveness
Career Placement
Faculty and Staff Satisfaction
Alumni Giving
Return Students

Delivering student and teaching
success is complicated
Business Scenario - First Year Student Attrition
Retain students/reduce dropout rates
Predict and target the needs of students more accurately.

Use analytics to uncover unexpected patterns and associations to guide interactions and improve results.
Identify drivers of student behavior via survey analysis and predictive modeling.

Predict student success through each stage of the student academic lifecycle.

Identify key issues including student retention and recruitment.

Better predict the outcome of student actions —drop out, performance interactions.

Analytics in Teaching and Learning
Predictive Analytics for Student Retention Solution
Predictive Analytics in Action
Demonstration Background

Goal
Significantly reduce student attrition

Requirements
Solution is able to quantify risk of students to drop out at any point in their student lifecycle
Solution is able to recommend optimal intervention for each student at risk
Solution should be easy to use by student advisors

Challenges
Disparate and inconsistent data
Inability to perform impact analysis on students and instructors
Inability to match learning style and past data with future success

Student Dashboard
360 Degree View
DATA ACCESS
DATA PREPARATION
MODELING
EXPORT
STUDENT ATTRITION MODEL OUTPUT
Example of a student segment
AC_Math = 18-19
FinAid_Awarded= Yes
HS_GPA <= 3.2
ACT_Reading= 20-21
AcceptanceType = Wait Listed
Housing = On Campusthen 90% probability of Term 1 Success

Example of a student segment
AC_Math = 18-19
FinAid_Awarded= No
ACT_Reading= 22-23
ScholarshipsOther = No
Gender = Malethen 18% probability of Term 1 Success

Model Predictions written into dataset
Education Sector Best Practice
Case Study - London South Bank University
Predictive Analytics
We already have a great deal of information on students:
Performance
Attendance
Engagement with core systems

Predictive Analytics takes this 'historic' information and maps onto current students.

Establishes 'alerts' as to performance - which can be monitored and responded to.
Increase in Student Progression
25%
The Strategy
- Assess the Situation
- Connect the Business
- Develop the Strategy
The Options
- Thought Leadership
- Industry Partnership
- Complete Solution
Significant improvement in attendance with proactive monitoring and intervention
900
Reports a day delivering essential insight across Uni operations
up to
8%
increase in graduation rate
25%
reduction in dropouts
1,900
users accessing data
90%
faster than ever before
Launching courses
76%
quicker than ever before and increasing demand for courses by
300%
of capacity
Next Steps
cailharg@uk.ibm.com
CaileanUK
07823 553500
Contact Details
Search -
IBM Exceptional Student Experience
Why IBM?
End to End Analytics

Learner Journey
Capture
Consistent Success

Curriculum Partner

Partnership Proposal
Predict
Act
Measure
Report
Business Success
Edinburgh Telford
Nottingham Trent Uni
Hamilton County Schools
Arizona State Uni
Universistat Leipzig
Co-Created
Co-Delivered
Co-Branded
Engaging
Curriculum
formerly
Full transcript