A Mathematical Framework for Temporal Modeling and Counterfactual Policy Simulation of Student Dropout

TL;DR

This paper introduces a temporal modeling framework with counterfactual policy simulation for student dropout, leveraging LMS engagement data and administrative records to evaluate intervention impacts.

Contribution

It presents a novel mathematical framework combining time-to-event modeling with counterfactual policy analysis for dropout prevention.

Findings

Model achieves high predictive accuracy with AUCs around 0.84.

Scenario simulations reveal potential survival benefits under specific policies.

Performance is sensitive to feature set composition, emphasizing temporal engagement signals.

Abstract

This study proposes a temporal modeling framework with a counterfactual policy-simulation layer for student dropout in higher education, using LMS engagement data and administrative withdrawal records. Dropout is operationalized as a time-to-event outcome at the enrollment level; weekly risk is modeled in discrete time via penalized, class-balanced logistic regression over person--period rows. Under a late-event temporal holdout, the model attains row-level AUCs of 0.8350 (train) and 0.8405 (test), with aggregate calibration acceptable but sparsely supported in the highest-risk bins. Ablation analyses indicate performance is sensitive to feature set composition, underscoring the role of temporal engagement signals. A scenario-indexed policy layer produces survival contrasts $\Delta S(T)$ under an explicit trigger/schedule contract: positive contrasts are confined to the shock branch ($T_{\rm policy}=18$: 0.0102, 0.0260, 0.0819), while the mechanism-aware branch is negative ($\Delta S_{\rm mech}(18)=-0.0078$, $\Delta S_{\rm mech}(38)=-0.0134$). A subgroup analysis by gender quantifies scenario-induced survival gaps via bootstrap; contrasts are directionally stable but small. Results are not causally identified; they demonstrate the framework's capacity for internal structural scenario comparison under observational data constraints.