Stripe cut fraud model training from 24h to 4.8h per epoch without shrinking data
emilygsands · x · 2026-10-20
Stripe engineers on scaling the Shield fraud model: iteration speed decides how much you can learn. A single epoch took 24 hours, making idea comparisons take days. They cut it to 4.8 hours without shrinking the dataset via S3 streaming, torch.compile, lower precision, lower peak memory, and tuned GPU communication.
Related event: Stripe Scales Shield Fraud Model, Boosting Recall Over 8%(7 posts)→
More from coding & agent
- Dev turns his Goodreads shelf into a slick site you can rebuild with Claude — thisiskp_ · 2026-10-20
- Notion AI ships major upgrade: smarter Agents, Auto 90% cheaper, BYOK support — ivanhzhao · 2026-10-20
- iPhone Action Button + Grok voice + HeyGen MCP turns a sentence into an avatar video — HeyGen · 2026-10-20
- Vibe-coded game League of Spawn adds Arenas: 15-minute MOBA team fights — majidmanzarpour · 2026-10-20
- esp32sim-mcp: MCP server lets AI agents build and test ESP32 firmware in a local emulator — EmanueleStrazzullo · 2026-10-20
- GameSummoner one-line local install: prompt-to-game pipeline runs fully local on a 5090 — demonicpigg · 2026-10-20