Mark Cheeseman OBE (PSFA) and Phillip Straley (FNA) examine the UK’s "cross-system" defense against public-sector fraud, highlighting how the Single Network Analytics Platform (SNAP) is uncovering hidden connections in minutes.

As fraud outpaces traditional compliance, central banks are shifting toward unified national infrastructures that leverage AI and real-time tracing to proactively protect consumers and restore financial system integrity.

FNA utilizes Graph Machine Learning instead of Federated Learning for real-time payment fraud detection because centrally analyzing hashed, multi-bank data reveals coordinated illicit networks and significantly increases predictive performance.

FNA joins the Emerging Payments Association Asia (EPAA) to help unify the payments agenda and drive advanced network analytics innovation across the APAC landscape.

The shift to instant payments has accelerated complex, cross-bank fraud that siloed bank data cannot detect. By establishing national data-sharing hubs and deploying advanced network analytics, authorities and banks can trace illicit money trails in real time and intercept scams before funds are lost.

FNA’s Will Towning examines BIS Project Aurora’s findings, which reveal that graph-based machine learning doubles the detection of money laundering activity while slashing false positives by up to 85%.

FNA and the ADGM Academy Research Centre enter a strategic partnership to drive UAE financial innovation through joint R&D, advanced network analytics, and digital twin technology.

The Bank of Papua New Guinea partners with FNA to deploy advanced network analytics and stress-testing simulations for real-time intraday liquidity monitoring and systemic risk oversight.

FNA’s independent review of CHIPS confirms its 'extreme efficiency' in liquidity usage, demonstrating how advanced simulation can validate economic cost savings in high-value settlement systems.