Synthetic Data in Education: Empirical Insights from Traditional Resampling and Deep Generative Models

TL;DR

This paper systematically compares traditional resampling and deep generative models for synthetic educational data, revealing trade-offs between utility and privacy, and recommending Variational Autoencoders as a balanced solution.

Contribution

It provides the first benchmark comparing resampling and deep generative models for educational data synthesis, offering practical guidance for privacy and utility trade-offs.

Findings

Resampling methods achieve near-perfect utility but no privacy protection.

Deep learning models like VAEs offer strong privacy but lower utility.

Variational Autoencoders balance utility (83.3%) and privacy protection.

Abstract

Synthetic data generation offers promise for addressing data scarcity and privacy concerns in educational technology, yet practitioners lack empirical guidance for selecting between traditional resampling techniques and modern deep learning approaches. This study presents the first systematic benchmark comparing these paradigms using a 10,000-record student performance dataset. We evaluate three resampling methods (SMOTE, Bootstrap, Random Oversampling) against three deep learning models (Autoencoder, Variational Autoencoder, Copula-GAN) across multiple dimensions: distributional fidelity (Kolmogorov-Smirnov distance, Jensen-Shannon divergence), machine learning utility such as Train-on-Synthetic-Test-on-Real scores (TSTR), and privacy preservation (Distance to Closest Record). Our findings reveal a fundamental trade-off: resampling methods achieve near-perfect utility (TSTR: 0.997) but completely fail privacy protection (DCR ~ 0.00), while deep learning models provide strong privacy guarantees (DCR ~ 1.00) at significant utility cost. Variational Autoencoders emerge as the optimal compromise, maintaining 83.3% predictive performance while ensuring complete privacy protection. We also provide actionable recommendations: use traditional resampling for internal development where privacy is controlled, and VAEs for external data sharing where privacy is paramount. This work establishes a foundational benchmark and practical decision framework for synthetic data generation in learning analytics.