AI layer

Every response carries inline scores produced by the intelligence layer. Scores are stable, auditable, and explainable.

fraud_score

0–100 score on every enrollment, claim, and payment. Higher means higher risk. Tunable thresholds available per partner.

identity_confidence

0–1 confidence on the verified identity of a member. Combines BVN, NIN, biometric, and historical signals.

lapse_risk_score

0–1 risk that a policy will lapse during the next collection cycle. Designed for proactive retention.

value_score

0–100 plan-quality score. Considers benefit breadth, network depth, and pricing efficiency.

Auditability

Every score includes the model version, inputs hash, and decision time. Full traces are queryable from the portal.