QFDNN: A Resource-Efficient Variational Quantum Feature Deep Neural Networks for Fraud Detection and Loan Prediction

2025-04-28

AI Summary

Financial data exhibit high dimensionality and noise sensitivity, while existing quantum machine learning models suffer from excessive resource consumption and poor robustness—particularly on near-term intermediate-scale quantum (NISQ) hardware. Method: We propose a resource-efficient, noise-resilient Quantum Feature Deep Neural Network (QFDNN), featuring a novel hybrid architecture that jointly optimizes quantum feature extraction and classical deep neural networks. It employs learnable quantum feature mappings and simplified variational quantum circuits to achieve compact, robust representations of high-dimensional financial data using only a small number of qubits. Contribution/Results: On fraud detection and loan prediction tasks, QFDNN achieves 82.2% and 74.4% accuracy, respectively. Compared to state-of-the-art quantum approaches, it significantly reduces computational overhead and maintains stable performance under six representative noise types. This work establishes a scalable, low-resource, and robust paradigm for trustworthy quantum machine learning in fintech during the NISQ era.

Technology Category

• Machine Learning: Quantum Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Safety and Robustness

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Social financial technology focuses on trust, sustainability, and social responsibility, which require advanced technologies to address complex financial tasks in the digital era. With the rapid growth in online transactions, automating credit card fraud detection and loan eligibility prediction has become increasingly challenging. Classical machine learning (ML) models have been used to solve these challenges; however, these approaches often encounter scalability, overfitting, and high computational costs due to complexity and high-dimensional financial data. Quantum computing (QC) and quantum machine learning (QML) provide a promising solution to efficiently processing high-dimensional datasets and enabling real-time identification of subtle fraud patterns. However, existing quantum algorithms lack robustness in noisy environments and fail to optimize performance with reduced feature sets. To address these limitations, we propose a quantum feature deep neural network (QFDNN), a novel, resource efficient, and noise-resilient quantum model that optimizes feature representation while requiring fewer qubits and simpler variational circuits. The model is evaluated using credit card fraud detection and loan eligibility prediction datasets, achieving competitive accuracies of 82.2% and 74.4%, respectively, with reduced computational overhead. Furthermore, we test QFDNN against six noise models, demonstrating its robustness across various error conditions. Our findings highlight QFDNN potential to enhance trust and security in social financial technology by accurately detecting fraudulent transactions while supporting sustainability through its resource-efficient design and minimal computational overhead.

Problem

• Addresses scalability and overfitting in fraud detection using quantum computing
• Improves noise resilience in quantum algorithms for financial data processing
• Reduces computational costs in loan prediction with efficient quantum models

Innovation

• Resource-efficient variational quantum neural network
• Noise-resilient with simpler variational circuits
• Optimizes feature representation using fewer qubits