Built a regulatory-compliant federated AI framework and published at IEEE at 15

Akul built a federated ensemble learning framework combining five heterogeneous base learners across 24 federated clients, using differential privacy with Renyi DP accounting, meta-learning aggregation via stacking and secure proxy training. Trained on 150,000 real-world GMSC loan samples plus 45,000 synthetic samples with non-IID heterogeneity, it reached 91.8% accuracy, just 1.7 percentage points off centralized performance. The framework simultaneously satisfies GDPR Article 32, ECOA anti-discrimination requirements and Basel III calibration standards.

FIELDAI & Financial Technology

RESULTFull paper accepted at IEEE RCSM 2025

VENUEIEEE RCSM 2025, 2025

Akul Nehra, YRI FellowIEEE RCSM

BEFORE THE FELLOWSHIP

A 9th grader at Genesis Global School with strong Python and ML skills but no peer-reviewed publications or formal research credentials.

AFTER

First-author IEEE publication on privacy-preserving federated learning with a framework satisfying three major regulatory standards at once.

THE LEDGER

01Full paper accepted for publication at IEEE RCSM 2025

0291.8% accuracy on 150,000 real-world samples across 24 federated clients

03Satisfies GDPR Article 32, ECOA and Basel III standards simultaneously

04Demographic parity gaps below 0.026 and expected calibration error below 0.032

05First framework to jointly optimize privacy, fairness and calibration for heterogeneous federated ensembles in finance

NEXT CASE STUDYAtharv Ved, Accepted at IEEE ICPCSN 2026

Every case study starts with one application.

ROLLING ADMISSIONS · SEATS LIMITED · NOW REVIEWING