Review of Gen AI Models for Financial Risk Management
DOI:
https://doi.org/10.32628/CSEIT2511114Keywords:
Gen AI, Financial Risk, GPT, LLMsAbstract
In this paper, we propose and demonstrate a prototype for leveraging Generative AI (GenAI) in financial risk analysis, specifically focusing on fine-tuning GPT models with proprietary data. Financial risk modeling, development, validation, and approval require not only advanced AI techniques but also careful implementation, given the vast and complex datasets involved in such tasks. The research underscores the critical importance of human oversight in mitigating potential failures that can arise from fully automated mathematical models.
The study explores the application of Large Language Models (LLMs) in various financial risk domains, such as credit risk assessment, market risk forecasting, and anomaly detection. While synthetic data generation is excluded from this work, the research highlights the use of zero-shot classification leveraging Hugging Face models and OpenAI tools. ChatGPT achieved over 70% accuracy in generating relevant questions and demonstrated 60% correctness in classification tasks. Additionally, we present a prototype pipeline that integrates GenAI capabilities into financial workflows, which is implementable on small-scale computing systems. This includes backend testing via Flask and rapid prototyping using cURL commands, offering a practical approach to testing and deploying models. By fine-tuning GenAI with domain-specific data and optimizing decision-making processes, this research highlights the transformative potential of integrating generative AI into financial risk management. The study provides insights into enhancing model efficiency, regulatory compliance, and scalability. Moreover, it addresses critical challenges such as handling large datasets and ensuring ethical AI use in decision-making systems. This work contributes to advancing the adoption of GenAI in financial analytics, paving the way for innovative, robust, and efficient methodologies to support the evolving demands of the financial sector.
Downloads
References
A. C. Teixeira, V. Marar, H. Yazdanpanah, A. Pezente, and M. Ghassemi, “Enhancing credit risk reports generation using LLMs: An integration of bayesian networks and labeled guide prompting,” in Proceedings of the fourth ACM international conference on AI in finance, in ICAIF ’23. New York, NY, USA: Association for Computing Machinery, Nov. 2023, pp. 340–348. doi: 10.1145/3604237.3626902. DOI: https://doi.org/10.1145/3604237.3626902
M. Sanz-Guerrero and J. Arroyo, “Credit risk meets large language models: Building a risk indicator from loan descriptions in P2P lending.” arXiv, Aug. 05, 2024. doi: 10.48550/arXiv.2401.16458. DOI: https://doi.org/10.2139/ssrn.4979155
G. Babaei and P. Giudici, “GPT classifications, with application to credit lending,” Machine Learning with Applications, vol. 16, p. 100534, Jun. 2024, doi: 10.1016/j.mlwa.2024.100534. DOI: https://doi.org/10.1016/j.mlwa.2024.100534
M. Khoja, “AI and bond values: How large language models predict default signals.” Social Science Research Network, Rochester, NY, Sep. 20, 2024. doi: 10.2139/ssrn.4965227. DOI: https://doi.org/10.2139/ssrn.4965227
B. Fazlija, M. Ibraimi, A. Forouzandeh, and A. Fazlija, “Implementing financial regulations using large language models.” Social Science Research Network, Rochester, NY, Nov. 05, 2024. Accessed: Dec. 19, 2024. [Online]. Available: https://papers.ssrn.com/abstract=5010694 DOI: https://doi.org/10.2139/ssrn.5010694
J. Ludwig, S. Mullainathan, and A. Rambachan, “Large language models: An applied econometric framework.” arXiv, Dec. 09, 2024. doi: 10.48550/arXiv.2412.07031. DOI: https://doi.org/10.3386/w33344
N. Li, C. Gao, M. Li, Y. Li, and Q. Liao, “EconAgent: Large language model-empowered agents for simulating macroeconomic activities,” in Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers), L.-W. Ku, A. Martins, and V. Srikumar, Eds., Bangkok, Thailand: Association for Computational Linguistics, Aug. 2024, pp. 15523–15536. doi: 10.18653/v1/2024.acl-long.829. DOI: https://doi.org/10.18653/v1/2024.acl-long.829
N. Li, C. Gao, Y. Li, and Q. Liao, “Large language model-empowered agents for simulating macroeconomic activities.” Social Science Research Network, Rochester, NY, Oct. 13, 2023. doi: 10.2139/ssrn.4606937. DOI: https://doi.org/10.2139/ssrn.4606937
N. Nascimento, C. Tavares, P. Alencar, and D. Cowan, “GPT in data science: A practical exploration of model selection,” in 2023 IEEE international conference on big data (BigData), Dec. 2023, pp. 4325–4334. doi: 10.1109/BigData59044.2023.10386503. DOI: https://doi.org/10.1109/BigData59044.2023.10386503
Y. Wang, J. Zhao, and Y. Lawryshyn, “GPT-signal: Generative AI for semi-automated feature engineering in the alpha research process.” arXiv, Oct. 24, 2024. doi: 10.48550/arXiv.2410.18448.
“GPT-4 and beyond: The role of generative AI in data engineering journal of bioinformatics and artificial intelligence.” Accessed: Dec. 21, 2024. [Online]. Available: https://biotechjournal.org/index.php/jbai/article/view/142
N. Dulam, V. Gosukonda, and M. Ankam, “GPT-4 and beyond: The role of generative AI in data engineering,” Journal of Bioinformatics and Artificial Intelligence, vol. 4, no. 1, pp. 227–249, Feb. 2024, Accessed: Dec. 21, 2024. [Online]. Available: https://biotechjournal.org/index.php/jbai/article/view/142
A. P. Desai, G. S. Mallya, M. Luqman, T. Ravi, N. Kota, and P. Yadav, “Opportunities and challenges of generative-AI in finance.” arXiv, Nov. 22, 2024. doi: 10.48550/arXiv.2410.15653. DOI: https://doi.org/10.1109/BigData62323.2024.10825658
D. P. Jeong, Z. C. Lipton, and P. Ravikumar, “LLM-select: Feature selection with large language models.” arXiv, Jul. 02, 2024. doi: 10.48550/arXiv.2407.02694.
D. Li, Z. Tan, and H. Liu, “Exploring large language models for feature selection: A data-centric perspective.” arXiv, Oct. 23, 2024. doi: 10.48550/arXiv.2408.12025.
A. Hinterleitner, T. Bartz-Beielstein, R. Schulz, S. Spengler, T. Winter, and C. Leitenmeier, “Enhancing feature selection and interpretability in AI regression tasks through feature attribution.” arXiv, Sep. 25, 2024. doi: 10.48550/arXiv.2409.16787.
S. Jomthanachai, W. P. Wong, and K. W. Khaw, “An application of machine learning regression to feature selection: A study of logistics performance and economic attribute,” Neural Comput & Applic, vol. 34, no. 18, pp. 15781–15805, Sep. 2022, doi: 10.1007/s00521-022-07266-6. DOI: https://doi.org/10.1007/s00521-022-07266-6
E. Sharkey and P. Treleaven, “BERT vs GPT for financial engineering.” arXiv, Apr. 24, 2024. doi: 10.48550/arXiv.2405.12990.
M. Hofert, “Assessing ChatGPT’s proficiency in quantitative risk management,” Risks, vol. 11, no. 9, p. 166, Sep. 2023, doi: 10.3390/risks11090166. DOI: https://doi.org/10.3390/risks11090166
O. Aljaloudi, M. Thiam, M. Qader, M. K. S. Al-Mhdawi, A. Qazi, and N. Dacre, “Examining the integration of generative AI models for improved risk management practices in the financial sector,” Nov. 2024. DOI: https://doi.org/10.2139/ssrn.5023563
J. Lee, N. Stevens, S. C. Han, and M. Song, “A survey of large language models in finance (FinLLMs).” arXiv, Feb. 04, 2024. doi: 10.48550/arXiv.2402.02315. DOI: https://doi.org/10.1007/s00521-024-10495-6
G. Bhatia, E. M. B. Nagoudi, H. Cavusoglu, and M. Abdul-Mageed, “FinTral: A family of GPT-4 level multimodal financial large language models.” arXiv, Jun. 14, 2024. doi: 10.48550/arXiv.2402.10986. DOI: https://doi.org/10.18653/v1/2024.findings-acl.774
“How to train generative AI using your company’s data.” Accessed: Dec. 22, 2024. [Online]. Available: https://hbr.org/2023/07/how-to-train-generative-ai-using-your-companys-data
“Proprietary data, your competitive edge in generative AI IBM.” Accessed: Dec. 22, 2024. [Online]. Available: https://www.ibm.com/think/insights/proprietary-data-gen-ai-competitive-edge
A. Selvaraj, D. Venkatachalam, and G. Namperumal, “Synthetic data for financial anomaly detection: AI-driven approaches to simulate rare events and improve model robustness,” Journal of Artificial Intelligence Research and Applications, vol. 2, no. 1, pp. 373–425, 2022, Accessed: Dec. 25, 2024. [Online]. Available: https://aimlstudies.co.uk/index.php/jaira/article/view/221
“Evaluating the impact of synthetic data on financial machine learning models: A comprehensive study of AI techniques for data augmentation and model training journal of artificial intelligence research and applications.” Accessed: Dec. 25, 2024. [Online]. Available: https://aimlstudies.co.uk/index.php/jaira/article/view/214
V. K. Potluru et al., “Synthetic data applications in finance.” arXiv, Mar. 20, 2024. doi: 10.48550/arXiv.2401.00081.
J. Su et al., “Large language models for forecasting and anomaly detection: A systematic literature review.” arXiv, Feb. 15, 2024. doi: 10.48550/arXiv.2402.10350.
O. Campesato, Python 3 and machine learning using ChatGPT/GPT-4. Walter de Gruyter GmbH & Co KG, 2024. DOI: https://doi.org/10.1515/9781501520112
J. Koskula, “Generative artificial intelligence in support of analytics : Copilot 365,” 2024, Accessed: Dec. 25, 2024. [Online]. Available: https://lutpub.lut.fi/handle/10024/168426
P. Winder, C. Hildebrand, and J. Hartmann, “Biased echoes: Generative AI models reinforce investment biases and increase portfolio risks of private investors.” Social Science Research Network, Rochester, NY, Sep. 26, 2024. doi: 10.2139/ssrn.4968821. DOI: https://doi.org/10.2139/ssrn.4968821
“Generating synthetic data in finance proceedings of the first ACM international conference on AI in finance.” Accessed: Dec. 25, 2024. [Online]. Available: https://dl.acm.org/doi/abs/10.1145/3383455.3422554
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
