2. Leveraging Software for Predictive Analytics George González, Director of Institutional Research & Effectiveness Michelle Callaway, Manager of Program Review San Jacinto College, Pasadena, Texas

3. San Jacinto College Three campuses in Pasadena and Houston, Texas
Fall 2017: 30,509 credit students
AY : 7,500 credentials awarded (Associates & Certificates)
2017: Aspen Institute Rising Star Award – Top 5 Community College in the Nation

4. History Limitations: Extensive Coding = Time Consuming
2011: Initial logistic regression models built using Base SAS programming to predict FTIC fall to spring persistence
Limitations:
Extensive Coding = Time Consuming
Doesn’t lend itself to collaboration
Editing the model requires re-parameterization
AtD Data Coach, Dr. Jing Luan, suggested SAS Enterprise Miner

5. Prep Work for Model Building
Strong partnership with ITS
Data included in Model
Demographic data
High School Course Taking Behavior
Financial Aid data
Dual Credit data
College readiness level
Outcome variables

6. SAS Enterprise Miner
2014: Used SAS Enterprise Miner to build decision-tree models for predicting FTIC fall to spring persistence
Benefits:
Less time coding = More time for analysis
Easy to collaborate
Build models in-house
Editing models is relatively quick
Low cost: SAS Enterprise Miner ~ $1500/license/year; Base SAS programming software ~ $800/license/year
Used results to identify our most at-risk students

7. Currently Building
Model to identify FTIC students at risk of failing or withdrawing from all courses in first term
Math pathways models to identify best math course for FTIC student success
Interactive tool that incorporates model results with student information system (SIS) data

8. SAS Enterprise Miner Workflow Example 

9. Future Work
Using predictive modeling to identify optimal combinations of student interventions
Incorporating non-cognitive measures into models

10. Questions?