Synthetic Data for Financial Anomaly Detection: AI-Driven Approaches to Simulate Rare Events and Improve Model Robustness
Keywords:
synthetic data, financial anomaly detectionAbstract
Financial anomaly identification repeating uncommon, high-impact occurrences using synthetic data increases model robustness. This work on financial anomaly identification simulates market failures, fraud, and systemic hazards using artificial intelligence investigates Since historical datasets lack such anomalies, synthetic data synthesis might overcome data constraints and enhance anomaly detection system training and performance.
The research emphasizes the need of synthetic data in financial systems in which unusual occurrences might have major influence on the economy. Because of its uneven composition, historical data models might not be able to predict unexpected occurrences. This paper proposes that GANs, VAEs, and agent-based modeling may close this gap by offering diverse and representative datasets capturing more anomalies.
References
A. Radford, L. Metz, and R. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” in Proc. Int. Conf. Learn. Represent., 2016.
I. Goodfellow et al., “Generative Adversarial Nets,” in Advances in Neural Information Processing Systems, 2014.
D. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” in Proc. Int. Conf. Learn. Represent., 2014.
X. Chen, X. Xu, and C. Zhang, “A Survey on Deep Learning for Financial Anomaly Detection,” IEEE Access, vol. 8, pp. 104100-104113, 2020.
H. Liu, L. Zhang, and W. Zhang, “Anomaly Detection for Financial Transactions Using Variational Autoencoders,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 754-765, 2021.
S. A. Shah, S. Sharma, and N. Gupta, “A Review of Anomaly Detection Techniques in Financial Data,” Journal of Computer and Communications, vol. 8, no. 5, pp. 63-72, 2020.
Y. Tang and J. Zhang, “Synthetic Data Generation for Financial Fraud Detection: A Review,” IEEE Access, vol. 8, pp. 114607-114622, 2020.
M. H. Amini, S. G. McGinty, and T. S. Miller, “Generative Models for Financial Anomaly Detection,” in Proc. IEEE Int. Conf. Data Mining Workshops, 2018.
Z. Li and X. Li, “Comparative Study of GANs and VAEs for Anomaly Detection in Financial Data,” IEEE Transactions on Computational Intelligence and AI in Games, vol. 12, no. 1, pp. 54-67, 2020.
L. Xie, S. M. Wang, and A. K. Gupta, “Agent-Based Models for Financial Market Simulations: A Review and Analysis,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 50, no. 5, pp. 1552-1564, 2020.
P. K. Sinha, S. M. Das, and A. S. Rao, “Evaluation Metrics for Anomaly Detection Models in Finance,” IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 4, pp. 876-889, 2021.
J. Zhang, L. Zhang, and C. Wang, “Latent Space Modeling for Synthetic Data Generation in Financial Applications,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 7, pp. 2200-2212, 2020.
J. W. Lee and Y. B. Kwon, “Synthetic Data and Its Role in Enhancing Financial Anomaly Detection,” IEEE Access, vol. 8, pp. 135742-135754, 2020.
M. D. Griffith, J. M. Martinez, and S. S. Singh, “Real-Time Anomaly Detection with Synthetic Data: Applications in Financial Fraud Detection,” IEEE Transactions on Computational Social Systems, vol. 8, no. 3, pp. 762-773, 2021.
C. Sun and J. G. Lee, “Evaluating the Impact of Synthetic Data on Financial Anomaly Detection Models,” in Proc. IEEE Int. Conf. Big Data, 2020.
K. H. Kim and J. H. Park, “Challenges and Opportunities in Financial Anomaly Detection with Synthetic Data,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, no. 6, pp. 1981-1992, 2020.
T. L. Miller, R. S. Williams, and M. J. White, “Advanced Synthetic Data Generation Techniques and Their Impact on Financial Systems,” IEEE Transactions on Artificial Intelligence, vol. 1, no. 2, pp. 156-168, 2020.
N. Gupta, R. S. Patel, and J. H. Choi, “Synthetic Data in Financial Modeling: A Comparative Study of GANs, VAEs, and Agent-Based Models,” IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 3, pp. 645-658, 2021.
L. M. Sanchez, K. L. Zhang, and D. A. Richards, “Ethical Considerations in Synthetic Data Generation for Financial Applications,” IEEE Transactions on Computational Intelligence and AI in Finance, vol. 6, no. 2, pp. 92-103, 2021.
S. Y. Lee and E. C. Rogers, “Integration of Synthetic Data with Financial Anomaly Detection Frameworks: A Survey,” IEEE Transactions on Data and Knowledge Engineering, vol. 34, no. 5, pp. 1534-1546, 2022.
