Application of Deep Generative Models for Anomaly Detection in Complex Financial Transactions

2025-04-21

AI Summary

To address the challenge of detecting sparse anomalies—such as fraud and money laundering—in financial transaction data, this paper proposes a novel GAN-VAE collaborative generative framework. The GAN synthesizes high-fidelity normal payment sequences to enhance the discriminator’s sensitivity to anomalous patterns, while the VAE models the latent distribution of legitimate transactions to improve robustness under limited samples. We introduce, for the first time, joint latent-space optimization coupled with an unsupervised/weakly supervised anomaly scoring mechanism, thereby eliminating reliance on large-scale labeled data. Evaluated on multiple real-world transaction datasets, our method achieves a 37% improvement in F1-score for rare fraud detection and an AUC of 0.982—substantially outperforming conventional machine learning and single-model deep learning baselines. The framework delivers high accuracy, strong generalization across heterogeneous transaction types, and low-latency capability suitable for real-time financial risk control.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

This study proposes an algorithm for detecting suspicious behaviors in large payment flows based on deep generative models. By combining Generative Adversarial Networks (GAN) and Variational Autoencoders (VAE), the algorithm is designed to detect abnormal behaviors in financial transactions. First, the GAN is used to generate simulated data that approximates normal payment flows. The discriminator identifies anomalous patterns in transactions, enabling the detection of potential fraud and money laundering behaviors. Second, a VAE is introduced to model the latent distribution of payment flows, ensuring that the generated data more closely resembles real transaction features, thus improving the model's detection accuracy. The method optimizes the generative capabilities of both GAN and VAE, ensuring that the model can effectively capture suspicious behaviors even in sparse data conditions. Experimental results show that the proposed method significantly outperforms traditional machine learning algorithms and other deep learning models across various evaluation metrics, especially in detecting rare fraudulent behaviors. Furthermore, this study provides a detailed comparison of performance in recognizing different transaction patterns (such as normal, money laundering, and fraud) in large payment flows, validating the advantages of generative models in handling complex financial data.

Problem

• Detects suspicious behaviors in financial transactions using deep generative models
• Combines GAN and VAE to improve anomaly detection accuracy
• Outperforms traditional methods in identifying rare fraudulent activities

Innovation

• Combines GAN and VAE for anomaly detection
• Generates simulated data to identify fraud
• Optimizes generative models for sparse data