Estimating Optimal Dynamic Treatment Regimes for Personalized Education: A Tutorial and Applications with Machine Learning

2026-10-07

AI Summary

This study addresses the limited application of dynamic treatment regimes in education and the lack of empirical support for personalized curriculum recommendation. We introduce optimal dynamic treatment regimes (ODTR) from biostatistics into longitudinal educational decision-making for the first time. Using the HSLS:09 dataset, we employ targeted maximum likelihood estimation (TMLE) and ensemble learning algorithms for model optimization, while incorporating domain knowledge to impose feasibility constraints and provide design guidelines for single- and multi-stage interventions. Our findings demonstrate that although unconstrained solutions yield higher theoretical value estimates, they remain impractical; conversely, constrained feasible pathways better align with real-world scenarios and receive expert endorsement. This work effectively balances theoretical optimality with practical implementability, significantly enhancing the deployability of personalized recommendations aimed at maximizing student achievement.

Abstract

Optimal dynamic treatment regimes (ODTRs) are increasingly used to generate sequences of personalized recommendations that maximize a final outcome of interest. Although ODTRs are widely used in biostatistics and precision medicine, their applications in education remain limited, especially for longitudinal decision-making. This study translates ODTR methods for single- and multi-stage designs into individualized high school math course recommendations, providing step-by-step guidelines and demonstrations with data from the High School Longitudinal Study of 2009 (HSLS:09). We use Targeted Maximum Likelihood Estimation with ensemble machine learning to estimate ODTRs that maximize students' math achievement and college enrollment, imposing feasibility constraints based on domain knowledge and propensity-score thresholds to ensure recommendations are practically implementable. Results show that unconstrained regimes yield higher estimated values but infeasible recommendations, while feasible regimes produce realistic pathways with stronger empirical and expert-informed support. Finally, we discuss practical considerations for designing ODTRs in education.

Problem

• Optimal Dynamic Treatment Regimes
• Personalized Education
• Longitudinal Decision-Making
• Course Recommendation

Innovation

• Optimal Dynamic Treatment Regimes
• Targeted Maximum Likelihood Estimation
• Ensemble Machine Learning
• Personalized Education
• Feasibility Constraints