A federated credit-risk cockpit for banking pilots. Each bank trains on its own shard of real Lending Club data; the center only ever sees scores, confidence, and explanations — and Calybris turns them into APPROVE, REVIEW, or DECLINE.
A single bank's default history is thin and biased toward its own customer base. Pooling raw borrower rows across banks would give a far better risk model — but regulation, privacy, and competition make that impossible. So each institution is stuck learning credit risk alone, on a narrow slice of reality.
Income-segmented banks train local models on their own data — raw rows never leave the bank.
The center consumes scores, confidence, drift, and explanation summaries — never borrower rows.
The boundary turns PD, stress PD, confidence, and thresholds into deterministic APPROVE / REVIEW / DECLINE.
Built on real Lending Club data, not synthetic telemetry.
Raw borrower rows never cross a bank boundary — only evidence does.
Every decision bound to a Calybris audit boundary and stress-tested with fault injection.
Let's talk about federated, explainable, audit-bound ML.