Use cases · Finance · financial crime
Screen for the coordinated fraud rings pairwise models miss
A method for reading collective behaviour in payment networks. We measured where pairwise models go wrong; no detection gain is claimed.
Impact
See where your pairwise model is blind
Baseline: a pairwise-additive prediction of the same network
Condition: the pairwise prediction was wrong by 72% on the collective response we measured
The problem
Fraud rings act together. Most transaction-risk models score accounts and pairs of accounts, which adds up individual signals and can miss behaviour that only appears when a group moves at once.
Our approach
We treat the payment network as a coupled system and read its collective response, on quantum hardware and in simulation, and compare that with what a pairwise-additive model predicts for the same network.
The evidence
- Pairwise-additive prediction error of 72% against the measured collective response, validated against exact references.
- Not claimed: a fraud-detection gain. This is a method result; a detection pilot on your data is the next step.
Status: Quantum hardware + Simulation. Method measured on quantum hardware and in simulation. No detection gain claimed.