Estimating Nationwide High-Dosage Tutoring Expenditures: A Predictive Model Approach

TL;DR

This paper develops a predictive model using XGBoost to estimate district-level high-dosage tutoring expenditures from incomplete data, aiding policy analysis during COVID-19 learning disruptions.

Contribution

It introduces a novel application of gradient-boosted decision trees to estimate unreported fiscal data in education policy contexts.

Findings

Estimated approximately $2.2 billion in tutoring expenditures.

Model achieved an out-of-sample R^2 of 0.358.

Demonstrated how machine learning can reconstruct fiscal patterns from sparse data.

Abstract

This study applies an optimized XGBoost regression model to estimate district-level expenditures on high-dosage tutoring from incomplete administrative data. The COVID-19 pandemic caused unprecedented learning loss, with K-12 students losing up to half a grade level in certain subjects. To address this, the federal government allocated \$190 billion in relief. We know from previous research that small-group tutoring, summer and after school programs, and increased support staff were all common expenditures for districts. We don't know how much was spent in each category. Using a custom scraped dataset of over 7,000 ESSER (Elementary and Secondary School Emergency Relief) plans, we model tutoring allocations as a function of district characteristics such as enrollment, total ESSER funding, urbanicity, and school count. Extending the trained model to districts that mention tutoring but omit cost information yields an estimated aggregate allocation of approximately \$2.2 billion. The model achieved an out-of-sample $R^2$=0.358, demonstrating moderate predictive accuracy given substantial reporting heterogeneity. Methodologically, this work illustrates how gradient-boosted decision trees can reconstruct large-scale fiscal patterns where structured data are sparse or missing. The framework generalizes to other domains where policy evaluation depends on recovering latent financial or behavioral variables from semi-structured text and sparse administrative sources.