Serve point-in-time features without temporal data leakage

FeatLock 1.0 is the live feature-serving console for FEATSRV — online Redis lookups, PIT training joins, leakage audits, and feature importance across underwriting, pricing, and fraud models from Zi Humana Research.

Top research capabilities

Zi Humana advances smarter actuarial ML through leakage-free point-in-time serving, dual Feast/PySpark engines, and Redis-backed online feature fetch for underwriting and fraud.

FeatLock 1.0™

Live feature-serving console for PIT training, online lookups, leakage audit, and importance.

1.0

Online Redis

Sub-10 ms policy and claim feature fetch from the materialised online store.

<10 ms

PIT training

As-of joins on SCD Type 2 entities for leakage-free training-set construction.

PIT

Leakage audit

Scan uploaded datasets for temporal traps against event timestamps.

Audit

REST /api/featsrv

Authenticated JSON endpoints for health, online, offline, PIT, audit, and importance.

REST

Nimbus packs

Seven synthetic actuarial packs with intentional leakage traps for evaluation.

7

Smarter impact powered by Zi Humana

API FeatLock 1.0 · /api/featsrv/*

Same-origin proxy at /api/featsrv forwards JSON and multipart payloads to the FEATSRV feature backend. Endpoints: /health, /online/policy/{id}, /online/claim/{id}, /offline, /pit-training, /leakage-audit, and /feature-importance. The console below mirrors the original FeatLock dashboard panels — overview, lineage, risk & leakage, importance, training, and online lookups.

Stay connected

What's New at Zi Humana — FeatLock 1.0 API releases, point-in-time feature serving research, and actuarial ML news.