A Privacy-Preserving Framework Using Remote Data Science for Inter-Institutional Student Retention Prediction

John Fields, K M Sajjadul Islam, Ruchitha Thota, Victor Chen, Praveen Madiraju
6/11/2026
cs.CRcs.LG

Official code: jtfields/NAIRR240195-Privacy-Preserving-Machine-Learning (0 stars, MIT, last commit 2026-05-20).

Abstract

This study explores privacy-preserving machine learning (PPML) techniques using the PySyft platform to enable collaborative prediction of student retention between institutions. We developed a remote data science (RDS) framework with a semi-air-gapped architecture consisting of high-side and low-side servers, allowing researchers from three universities to build predictive models on sensitive student data without direct data access. Using historical data from a small private university (N=720), we evaluated three synthetic data generation approaches and validated the framework through inter-institutional collaboration. The results demonstrate consistent classification performance across institutions (Macro F1: 0.690--0.695) while maintaining strict Family Educational Rights and Privacy Act (FERPA) compliance. We also propose Data-Type-Aware Templates, a novel synthetic data method that prioritizes privacy over distributional fidelity. Our findings confirm that RDS-based PPML is technically feasible for educational settings and offers a practical alternative to federated learning for small-scale inter-institutional collaborations. The code is available at https://github.com/jtfields/NAIRR240195-Privacy-Preserving-Machine-Learning.

View on arXivView PDF

Code Implementations(1)

jtfields/NAIRR240195-Privacy-Preserving-Machine-LearningOfficial100%
MIT

Testing Privacy Preserving Machine Learning on Education Data

00Jupyter NotebookOct 22, 20245 months agoMIT

Similar Papers

Fedlearn-Algo: A flexible open-source privacy-preserving machine learning platform

85% match1 repo922021

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service

85% match1 repo1862023

Vertical Federated Learning in Practice: The Good, the Bad, and the Ugly

85% match2025

Privacy Preserving Machine Learning Model Personalization through Federated Personalized Learning

85% match2025

TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning

84% match2025

Federated learning-outcome prediction with multi-layer privacy protection

84% match2023

Cite this paper

@article{fields2026privacypreserving,
  title  = {A Privacy-Preserving Framework Using Remote Data Science for Inter-Institutional Student Retention Prediction},
  author = {John Fields and K M Sajjadul Islam and Ruchitha Thota and Victor Chen and Praveen Madiraju},
  year   = {2026},
  eprint = {2606.12845},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2606.12845v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2606.12845.svg)](https://codeofpaper.com/paper/2606.12845)

Discussion