Application of Machine Learning in Financial Risk Classification and Account Verification Optimization Strategy
DOI:
https://doi.org/10.71222/bqr6ph45Keywords:
financial risk management, account verification, machine learning, multimodal data, risk detectionAbstract
With the rapid advancement of technology, effective financial risk control and ensuring account security have become key issues of concern in the financial industry. In the face of increasingly complex financial scenarios and constantly updated attack strategies, previous risk assessment and account verification methods are becoming less effective. This study developed an account security authentication mechanism following financial risk classification methodology. More specifically, an account verification architecture that integrates multiple sources of information is created using a comprehensive risk assessment framework that integrates machine learning techniques. This architecture combines biometric technology, user behavior pattern analysis, and device usage data to enhance the account verification process, including accuracy and speed of risk discrimination. In addition, by introducing adaptive optimization mechanisms, the model can self-adjusted and improve in real time. Overall, the strategy proposed in this study has implications for improving the security protection capability and intelligence level of financial systems.
References
1. M. Murdock, N. Thanh, and R. Nivine, "The effect of state-level corruption on performance and risk of financial institutions," J. Financial Crime, vol. 30, no. 6, pp. 1784-1807, 2023, doi: 10.1108/JFC-09-2022-0237.
2. N. A. Karim et al., "Online Banking User Authentication Methods: A Systematic Literature Review," IEEE Access, vol. 12, pp. 741-757, 2024, doi: 10.1109/ACCESS.2023.3346045.
3. J. R. Jensen and O. Ross, "Managing Risk in DeFi," in CEUR Workshop Proc., Aachen, 2020, doi: 10.2139/ssrn.3745568.
4. Y. Peng, G. Wang, G. Kou, and Y. Shi, "An empirical study of classification algorithm evaluation for financial risk prediction," Appl. Soft Comput., vol. 11, no. 2, pp. 2906-2915, 2011, doi: 10.1016/j.asoc.2010.11.028.
5. A. Adogame, "The 419 code as business unusual: youth and the unfolding of the advance fee fraud online dis-course," Asian J. Social Sci., vol. 37, no. 4, pp. 551-573, 2009, doi: 10.1163/156853109X460192.
6. A. Mashrur, W. Luo, N. A. Zaidi, and A. Robles-Kelly, "Machine Learning for Financial Risk Management: A Survey," IEEE Access, vol. 8, pp. 203203-203223, 2020, doi: 10.1109/ACCESS.2020.3036322.
7. C. Souza, "AI model risk: What the current model risk management framework can teach us about managing the risks of AI models," J. Financial Compliance, vol. 6, no. 2, pp. 103-112, 2023, doi: 10.69554/SOKX4074.
8. J. Fan and R. Li, "Statistical challenges with high dimensionality: Feature selection in knowledge discovery," arXiv preprint math, 2006, no. 0602133, doi: 10.4171/022-3.
9. M. A. Mezher, "Forecasting financial markets and credit risk classification using genetic folding algorithm," Int. J. Electron. Banking, vol. 3, no. 4, pp. 283-300, 2022, doi: 10.1504/IJEBANK.2022.128566.
10. A. Levy and R. Baha, "Credit risk assessment: A comparison of the performances of the linear discriminant analysis and the logistic regression," Int. J. Entrepreneurship and Small Business, vol. 42, no. 1-2, pp. 169-186, 2021, doi: 10.1504/IJESB.2021.112265
11. S. Shi et al., "Machine learning-driven credit risk: A systemic review," Neural Comput. Appl., vol. 34, no. 17, pp. 14327-14339, 2022, doi: 10.1007/s00521-022-07472-2.
12. J. Yang et al., "Auto insurance fraud detection with multimodal learning," Data Intell., vol. 5, no. 2, pp. 388-412, 2023, doi: 10.1162/dint_a_00191.
13. S. Boosa, "AI-powered risk management in fintech: Leveraging big data for fraud detection," Int. J. Sci. Eng., vol. 10, no. 3, pp. 77-88, 2024, doi: 10.53555/ephijse.v10i3.262.
