SuperML
← All issues

Why Fraud Rings Survive XGBoost — and How GNNs Stop Them

Row-based ML misses coordinated fraud rings — GNNs expose them by propagating relational signals through transaction graphs. Full walkthrough with PyTorch Geometric code and five production gotchas banks actually hit.

Hi there,

Your XGBoost fraud model is probably catching around 60% of what's hitting you. The 40% it misses isn't bad actors with unusual behavior — it's rings of accounts that each look normal but are systematically connected. Graph Neural Networks were built for exactly this gap, and the production architecture to make them work is teachable.

🔥 Featured Post

Why Fraud Rings Survive XGBoost — and How GNNs Stop Them

  • Fraud rings exploit the fact that row-based ML ignores relationships between rows — GNNs fix this by making each account's embedding a compressed fingerprint of its entire network neighborhood
  • HeteroConv + GAT is the production-ready architecture for banking graphs with mixed node types (accounts, devices, merchants)
  • AUPRC — not accuracy, not even F1 — is the right north-star metric for fraud at 0.1–2% base rates
  • Five deployment gotchas that matter more than architecture: temporal leakage, cold start, heterophily, scalability, and graph drift monitoring
  • Full PyTorch Geometric walkthrough: graph modeling, training loop, class imbalance handling, evaluation

Read the full post →

📚 In Case You Missed It

Copilot Drops GPT-4 for Polaris — What Changes for Enterprise Dev Pipelines — Microsoft Build 2026 shipped Project Polaris — Copilot's homegrown GPT-4 replacement — and enterprise teams need to treat the August cutover as a model substitution event, not an upgrade, before their agentic dev pipelines hit behavioral regression.

When Your Coding Agent Tops GitHub, Who Governs What It Ships to Production? — Claude Code is writing 4% of GitHub commits and Opus 4.8 can now run hundreds of parallel agents on codebase-scale migrations — here's the production governance gap enterprises are about to hit.

OpenAI's Safety Framework Creates New Accountability for Enterprise Buyers — OpenAI's Frontier Governance Framework aligns its safety practices to California and EU AI law — but a vendor compliance document creates new accountability for enterprise buyers, not just sellers.

More posts dropping every day. Stay curious.

— Bhanu @ superml.dev