Research Article

Quantum-Inspired Variational Autoencoders for Anomaly Detection in High-Dimensional Financial Transaction Data

101 reads
J Ong Artific Int Innov, 2026, 1 (2), 73-79, ISSN

Abstract

Detecting fraudulent patterns and irregular operational anomalies in high-dimensional financial transaction data represents a persistent challenge due to extreme class imbalance, multi-modal feature correlations, and dynamic adversarial shifts. Classical deep generative models, such as Variational Autoencoders (VAEs), often suffer from posterior collapse and struggle to capture intricate, non-linear dependencies across hundreds of continuous and categorical transaction features. In this work, we propose a novel Quantum-Inspired Variational Autoencoder (QI-VAE) tailored for unsupervised anomaly detection in complex financial streams. Our architecture integrates classical tensor network representations—specifically Matrix Product States (MPS)—into the latent generative pipeline, coupled with a density matrix formalism that enforces quantum-inspired unitary rotations and von Neumann entropy regularization across the latent manifolds. By simulating quantum superposition and entanglement principles on classical computing hardware, the QI-VAE effectively maps high-dimensional transactions into a compact, highly expressive latent state space where normal behaviors form constrained, coherent trajectories. Evaluated on large-scale real-world financial transaction benchmarks, including the Credit Card Fraud Detection and IEEE-CIS Fraud datasets, the proposed QI-VAE framework achieves an average improvement of 5.8% in Area Under the Precision-Recall Curve (PR-AUC) and a 4.2% gain in F1-score over state-of-the-art classical generative and tree-based baselines, while requiring up to 35% fewer trainable parameters. These findings demonstrate the viability of quantum-inspired inductive biases for enterprise financial monitoring systems.

Keywords variational autoencoder anomaly detection Quantum-Inspired Machine Learning Financial Fraud Detection Tensor Networks
Authors 2

The team behind this paper

2 authors, 2 institutions.

This paper Sorbonne Université — France Sorbonne Université 1 author Indian Institute of Technology Bombay — India Indian Institute of Tec… 1 author Prof. Hélène Vance-Moreau — corresponding author HV Prof. Hélène Vance-Moreau ✉ Dr. Sunita Deshmukh SD Dr. Sunita Deshmukh

Readership

101 reads over 3 months.

September 2026 November 2026

Bibliographic Information

Prof. Hélène Vance-Moreau, Dr. Sunita Deshmukh, (2026). Quantum-Inspired Variational Autoencoders for Anomaly Detection in High-Dimensional Financial Transaction Data, Journal of Ongoing Artificial Intelligence Innovations, 1(2): 73-79
Bibtex Citation
@article{prof._hélène_vance-moreau2026joaii,
author = {Prof. Hélène Vance-Moreau and Dr. Sunita Deshmukh},
title = {Quantum-Inspired Variational Autoencoders for Anomaly Detection in High-Dimensional Financial Transaction Data},
journal = {Journal of Ongoing Artificial Intelligence Innovations},
year = {2026},
volume = {1},
number = {2},
pages = {73-79},
doi = {},
url = {https://scimatic.org/show_manuscript/10264}
}
APA Citation
Vance-Moreau, P.H., Deshmukh, D.S., (2026). Quantum-Inspired Variational Autoencoders for Anomaly Detection in High-Dimensional Financial Transaction Data. Journal of Ongoing Artificial Intelligence Innovations, 1(2), 73-79. https://doi.org/

Author Information

  • To change your profile photo, login to scimatic.org, go to your profile and change the photo.
  • Any photo that shows your face will do: we crop it to your head and shoulders and give it a plain background automatically.
  • To sign in, go to Sign in and enter the e-mail address registered with the article: we e-mail you a one-time sign-in link (there is no password).
  • In case of any other problem, contact your editor directly or write to us at info @ scimatic.org