Financial Digital Twins: AI and Simulation-Based Risk Management for Banking Systems
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V6I2P104Keywords:
Financial Digital Twins, Monte Carlo simulations, Agent-based modelling, Credit risk assessment, Fraud detection, Predictive analytics, Decentralized finance (DeFi)Abstract
The increased volatility in the financial world, alongside the dynamics that characterize the global economy, have motivated the concept of Financial Digital Twins (FDTs) as AI-based, virtual models of the banking systems aimed to optimize risk management, fraud detection, and operational performance. With real-time data, operational research for risk assessment, and artificial intelligence systems, FDTs are useful in helping financial institutions anticipate risks, manage their decision systems, and design a better model for compliance with regulations. In the following paper, a literature review will look into using AI and ML to enhance the effective development of Financial Digital Twins. It discusses some modelling approaches that can be used in the industry, including Monte Carlo simulations, agent-based modelling, and the scenario approach, which help financial institutions model the market risk and credit performance alongside conditions in an economic downturn. Moreover, it reveals that AI can benefit credit scoring, fraud detection, and stress testing to increase the evaluation of risks. Still, when it comes to the drawbacks of the FDT, they are all associated with data protection, data processing, scalability, compliance issues, and AI model quality, respectively. This paper also covers new technologies like quantum computing, blockchain integration, and decentralized finance (DeFi), which have enhanced the existing dimensions of risk management in finance. Financial institutions must meet these challenges and adapt high technologies to advance banking systems to be financially sound, more informed, and more protective of banking systems
References
[1] Murphy, A., Taylor, C., Acheson, C., Butterfield, J., Jin, Y., Higgins, P. ... & Higgins, C. (2020). Representing financial data streams in digital simulations to support data flow design for a future Digital Twin. Robotics and Computer-Integrated Manufacturing, 61, 101853.
[2] Badakhshan, E., & Ball, P. (2023). Applying digital twins for inventory and cash management in supply chains under physical and financial disruptions. International Journal of Production Research, 61(15), 5094-5116.
[3] The Power of Digital Twins in BFSI: Driving Precision, Security, and Agility, online. https://www.linkedin.com/pulse/power-digital-twins-bfsi-driving-precision-security-kumar-she-her--fqy3c
[4] How Banks Use Real-Time Data to Improve Credit Risk & Minimise Loan Defaults, anaptyss, online. https://www.anaptyss.com/blog/banks-using-real-time-data-improve-credit-risk-minimize-defaults/
[5] Fikri, N., Rida, M., Abghour, N., Moussaid, K., & El Omri, A. (2019). An adaptive and real-time-based architecture for financial data integration. Journal of Big Data, 6, 1-25.
[6] Aziz, S., & Dowling, M. (2019). Machine learning and AI for risk management (pp. 33-50). Springer International Publishing.
[7] Vesna, B. A. (2021). Challenges of financial risk management: AI applications. Management: Journal of Sustainable Business and Management Solutions in Emerging Economies, 26(3), 27-34.
[8] Digital Twins: Catalyzing AI for financial risk management, banking dive, 2023. online. https://www.bankingdive.com/spons/digital-twins-catalyzing-ai-for-financial-risk-management/697416/
[9] Mashrur, A., Luo, W., Zaidi, N. A., & Robles-Kelly, A. (2020). Machine learning for financial risk management: a survey. Ieee Access, 8, 203203-203223.
[10] Hilal, W., Gadsden, S. A., & Yawney, J. (2022). Financial fraud: a review of anomaly detection techniques and recent advances. Expert systems With applications, 193, 116429.
[11] Phil Britt, 5 AI Case Studies in Banking, online. https://www.vktr.com/ai-disruption/5-ai-case-studies-in-banking/
[12] Thilagavathi, M., Saranyadevi, R., Vijayakumar, N., Selvi, K., Anitha, L., & Sudharson, K. (2024, April). AI-driven fraud detection in financial transactions with graph neural networks and anomaly detection. In 2024 International Conference on Science Technology Engineering and Management (ICSTEM) (pp. 1-6). EEE.
[13] Kanno, M. (2015). Macro stress test for credit risk. The Journal of Risk Finance, 16(5), 554-574.
[14] Kamuangu, P. (2024). A Review on Financial Fraud Detection using AI and Machine Learning. Journal of Economics, Finance and Accounting Studies, 6(1), 67-77.
[15] Twinize: Digital Twin Technology is available in banking, Galactica, and online. https://www.galaksiya.com/articles/twinize-digital-twin-technology-in-banking
[16] Sorge, M. (2004). Stress-testing financial systems: an overview of current methodologies.
[17] da Cruz, J. P., & Lind, P. G. (2012). The dynamics of financial stability in complex networks. The European Physical Journal B, 85, 1-9.
[18] Munjishvili, T. (2018). Predicting of Enterprise's Financial Stability by Simulation Models. Globalisation and Business, 3(5), 198-202.
[19] Anshari, M., Almunawar, M. N., & Masri, M. (2022). Digital twin: Financial technology's next frontier of robo-advisor. Journal of risk and financial management, 15(4), 163.
[20] Ikudabo, A. O., & Kumar, P. (2024). AI-driven risk assessment and management in banking: balancing innovation and security. International Journal of Research Publication and Reviews, 5(10), 3573-88.
