Search and Filter

Browse institutions A–Z

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

801 views · 167 downloads

Abstract: This study focuses on improving the predictive power of early warning systems (EWSs) to decrease chronic absenteeism in early childhood. Using a demographically diverse sample of students followed from PreK to third grade in Boston Public Schools (N=6,698), we demonstrate how and why two modern machine learning algorithms—the Synthetic Minority Oversampling Technique (SMOTE) and Extreme Gradient Boosting (XGBoost)—can enhance EWS accuracy. The best-performing XGBoost model with SMOTE achieved a 54 percentage point improvement in accuracy (in terms of recall rate) over the logistic regression model closest to those used in current EWSs, more accurately identifying students would become chronically absent in third grade. Notably, models excluding student demographic information maintained comparable predictive accuracy.

Research Categories

Keywords
chronic absenteeism, machine learning, early warning system, XGBoost, SMOTE, fairness
Education level
Topics

Citation

Document Object Identifier (DOI)
10.26300/xxvz-cv94
EdWorkingPaper suggested citation:
Wu, Tiffany, and Christina Weiland. (). Leveraging Modern Machine Learning to Improve Early Warning Systems and Reduce Chronic Absenteeism in Early Childhood. (EdWorkingPaper: -1081). Retrieved from Annenberg Institute at Brown University: https://doi.org/10.26300/xxvz-cv94

Machine-readable bibliographic record: RIS, BibTeX