Lecture / Reading

Leveraging Modern Machine Learning to Improve Early Warning Systems and Reduce Chronic Absenteeism in Early Childhood

  • Date: Tuesday, January 20, 2026
  • Time: 9:00am — 9:30am PST

This event has already occurred.

Featuring

  • Tiffany Wu Student

Chronic absenteeism is a critical issue that has been linked to many adverse student outcomes. This talk focuses on improving a key system already in place in many school districts—early warning systems (EWSs)—in order to decrease chronic absenteeism in early childhood. Using a demographically diverse population of students followed from Pre-K to third grade in Boston Public Schools (N=6,698), I demonstrate how and why modern machine learning algorithms such as the Synthetic Minority Oversampling Technique (SMOTE) and Extreme Gradient Boosting (XGBoost) can improve EWS accuracy in proactively identifying students who are at risk of becoming chronically absent in third grade, thus facilitating more timely supports. Central to the talk is a critical examination of how student demographic information is used in predictive models and the implications for designing EWSs that are effective and equitable.