Quantum Machine Learning for Few-Shot Impersonation Detection in Digital Account Opening
Abstract
Identity impersonation fraud may emerge only after digital account opening, requiring an early post-onboarding approach based on behavioral and transactional signals observed shortly after activation. Confirmed cases remain rare, creating extreme class imbalance and material operational risk for digital banks. We evaluate quantum machine learning (QML) against classical one-class methods in this setting using a real 2025 cohort of 3,419 digital account openings from Banco de Creditos e Inversiones (BCI), Chile, including 8 confirmed impersonation-fraud cases (0.23% prevalence). The data were provided through an industry-research collaboration between BCI and CoreDevX LABTAV under operational constraints. The best-performing configuration used only 2 qubits and was executed on CoreDevX's SpinQ Triangulum II, a 3-qubit nuclear magnetic resonance (NMR) device, enabling hardware validation beyond classical simulation. The quantum one-class classifier based on Automatic Quantum Feature Mapping (AQFM) achieves 88% recall (7 of 8 frauds detected) and 9.21% precision, corresponding to approximately 70% fewer false positives than the best-performing classical baseline at comparable recall. When its 2025-calibrated decision threshold is applied unchanged to the independent 2026 cohort, AQFM detects 20 of 31 frauds (64.5% recall) with 8.81% precision and remains the best-performing model among those evaluated.
Related
- Generative Quantum Machine Learning Methods for Cancer Detection using Augmented Datasets
- Simulation-Based Quantum Forensics for QKD: Machine Learning Attack Detection and Signature Extraction
- Digital Twins of Networked Dynamical Systems: Machine Learning Prediction of Synchronization Transitions in Coupled Chaotic Oscillators
- RAFT-DVC: Resolution-Aware Machine Learning-Based Digital Volume Correlation
- Image-Derived PM10 Estimation in Cattle Feedlot Using Machine Learning: Addressing Concentration Ranges Beyond Existing Digital Imaging Methods
BibTeX
@misc{canales2026quantum,
title = {{Quantum Machine Learning for Few-Shot Impersonation Detection in Digital Account Opening}},
author = {Javiera Canales and Jose Ortega and Maximiliano Araya},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.07242},
eprint = {2610.07242},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.07242},
}
RIS
TY - UNPB
TI - Quantum Machine Learning for Few-Shot Impersonation Detection in Digital Account Opening
AU - Javiera Canales
AU - Jose Ortega
AU - Maximiliano Araya
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.07242
UR - https://arxiv.org/abs/2610.07242
AB - Identity impersonation fraud may emerge only after digital account opening, requiring an early post-onboarding approach based on behavioral and transactional signals observed shortly after activation. Confirmed cases remain rare, creating extreme class imbalance and material operational risk for digital banks. We evaluate quantum machine learning (QML) against classical one-class methods in this setting using a real 2025 cohort of 3,419 digital account openings from Banco de Creditos e Inversiones (BCI), Chile, including 8 confirmed impersonation-fraud cases (0.23% prevalence). The data were provided through an industry-research collaboration between BCI and CoreDevX LABTAV under operational constraints. The best-performing configuration used only 2 qubits and was executed on CoreDevX's SpinQ Triangulum II, a 3-qubit nuclear magnetic resonance (NMR) device, enabling hardware validation beyond classical simulation. The quantum one-class classifier based on Automatic Quantum Feature Mapping (AQFM) achieves 88% recall (7 of 8 frauds detected) and 9.21% precision, corresponding to approximately 70% fewer false positives than the best-performing classical baseline at comparable recall. When its 2025-calibrated decision threshold is applied unchanged to the independent 2026 cohort, AQFM detects 20 of 31 frauds (64.5% recall) with 8.81% precision and remains the best-performing model among those evaluated.
ER -