Alan Fritzler Anushka Anand Reid Johnson Siobhan Greatorex-Voith Robin Gong Kerstin Frailey
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Arlington, Cabarrus County, Vancouver, Wake County
Data-Driven Strategies for Predicting On-Time High School Graduation
Over 700,000!
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Students in the U.S. Do Not Complete High School Each Year*
* G. Kena, L. Musu-Gillette, J. Robinson, et al. The Condition of Education 2015. (NCES 2015-144). U.S. Department of Education, National Center for Education Statistics, Washington, D.C., 2015.
Looking Beyond a Single School
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Students at Risk
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Students at Risk
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Non-completer
Students at Risk
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Graduated Late
Non-completer
Grade-Level Data
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Grade Level 6 7 8 9 10 11 12
Absences Grades Tardies
Test Scores …
Absences Grades Tardies
Test Scores …
Absences Grades Tardies
Test Scores …
Absences Grades Tardies
Test Scores …
Absences Grades Tardies
Test Scores …
Absences Grades Tardies
Test Scores …
Absences Grades Tardies
Test Scores …
Date of Birth, Gender, Race/Ethnicity, …
Grade-Level Features
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Grade Level 6 7 8 9 10 11 12
Features Features Features Features Features Features Features
Predict
On Time Not On Time
Model Evaluation
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Name Score Actual Jayne Cobb .97 Yes
River Tam .92 Yes
Olivia Dunham .90 Yes
Maeby Funke .87 No
Inara Serra .82 Yes
Malcolm Reynolds .79 No
Kaylee Frye .79 No
Maggie Lizer .62 Yes
Nina Sharp .40 No
Peter Bishop .21 No
Bad: On-track student predicted higher risk than off-track student.
Good: Off-track students have the highest predicted risk.
Risk Scoring
Modeling Results
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
0
0.2
0.4
0.6
0.8
1
6 7 8 9 10 11
Grade Level
Prec
ision
at T
op 1
0%
Our Approach
Baseline
School-Level Insights
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
Student-Level Insights
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015
District-Level Insights
The Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship 2015