Quantum

Quantum Machine Learning for Few-Shot Impersonation Detection in Digital Account Opening

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 07/10/2026, 04:13:25 UTC.

Briefings

A 2026 study by CoreDevX LABTAV and Banco de Creditos e Inversiones (BCI) in Chile evaluated quantum machine learning for detecting identity impersonation fraud in digital account openings. Using a 2025 cohort of 3,419 account openings, the research found that the quantum one-class classifier based on Automatic Quantum Feature Mapping (AQFM) achieved 88% recall and 9.21% precision, detecting 7 of 8 confirmed fraud cases. This performance was superior to classical one-class methods, resulting in approximately 70% fewer false positives. The model was validated on hardware using only 2 qubits on a 3-qubit NMR device, and when applied to a 2026 independent cohort, it detected 64.5% of frauds with 8.81% precision.

Key points

• The quantum one-class classifier based on Automatic Quantum Feature Mapping (AQFM) achieved 88% recall and 9.21% precision in detecting identity impersonation fraud.
• The model was validated on hardware using only 2 qubits on a 3-qubit NMR device, enabling hardware validation beyond classical simulation.

Context and limitations

The study utilized a 2025 cohort of 3,419 account openings from Chile, and results were applied unchanged to a 2026 independent cohort without further validation.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 07/10/2026, 05:09:47 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeiedrv7azep2coz5luncrznr54jvk3ddjpobdlw632thytz56u5cre