Patrice Easley

Professional Summary

Patrice Easley is a pioneering fintech security architect specializing in federated learning for cross-border payment risk assessment. By merging privacy-preserving AI with global compliance frameworks, Patrice designs decentralized machine learning systems that enable financial institutions to collaboratively detect fraud and money laundering—without sharing raw transaction data. Her work redefines how banks combat financial crime while adhering to GDPR, CCPA, and other stringent data sovereignty laws.

Core Innovations & Methodologies

1. Privacy-First Risk Modeling

• Develops federated learning frameworks that:

  • Train global fraud detection models on distributed data (SWIFT, SEPA, Alipay)

  • Preserve anonymity through homomorphic encryption and secure multi-party computation (SMPC)

  • Detect cross-jurisdictional laundering patterns via gradient-sharing protocols

2. Regulatory-Adaptive Systems

• Builds dynamic compliance engines that:

  • Auto-adjust to local regulations (e.g., EU’s AMLD6, US Bank Secrecy Act)

  • Generate audit-ready reports with differential privacy guarantees

  • Flag high-risk corridors (e.g., crypto-fiat gateways) using federated graph analytics

3. Real-Time Threat Intelligence

• Implements edge-computing pipelines for:

  • Instant risk scoring during transaction routing

  • Collaborative blacklist updates without exposing sensitive data

  • Anomaly detection in stablecoin flows and hawala networks

Career Milestones

• Led the Federated AML Consortium, reducing false positives by 38% across 12 major banks

• Patented a blockchain-anchored federated ledger for model version control

• Pioneered the "Privacy Score" metric now adopted by FATF for evaluating FL systems