Using Machine Learning to Advance High School Dropout Prediction and Prevention (Poster 1)

• In Event: AERA Promising Scholarship in Education Research: Dissertation Fellows and Their Research
  In Invited Poster Session: AERA Promising Scholarship in Education Research: Dissertation Fellows and Their Research Poster Session

Abstract

This study applies machine learning techniques to statewide longitudinal data systems (SLDS) to identify students at risk of dropping out of high school in either 9th or 10th grade. I find that logistic regression performs similarly to more complex algorithms after applying oversampling techniques. Post-hoc analyses reveal that a student’s age in 8th grade followed by middle grade absences, especially chronic absenteeism, is predictive of early exit. This advances the current state of knowledge in the field by (1) generating synthetic data to improve model accuracy, (2) ensuring that model predictions prevent the widening of structural inequities, and (3) exploring novel approaches to enhance the explainability associated with “black box” models, ultimately generating actionable insights for practitioners and stakeholders.

Author

• Anika Alam, University of Pennsylvania