Agentic Artificial Intelligence For Automated Banking Risk Assessment And Decision Support: A Human-In-The-Loop Framework For Credit, Compliance, And Regulatory Governance
DOI:
https://doi.org/10.63665/IJAICE.0203.12Keywords:
Agentic AI, Banking Risk, Human-In-The-Loop, Xgboost, Explainability, Compliance, Governance, Fairness, Decision Support, AuditabilityAbstract
In this paper, a human-in-the-loop Agentic AI model of banking risk assessment, compliance and decision support is developed and evaluated. They were evaluated using 8,000 synthetic records, logistic regression, random forests, XGBoost and Isolation Forest. XGBoost had an accuracy of 61.25% and a ROC-AUC of 0.631 which has a weak autonomous reliability. Accuracy is raised to 85.83% and F1-score to 87.94% in case of human supervision, whereas, 97.17% escalation coverage signified operational dependency. The design synthesizes out the explainability, fairness, auditability, cybersecurity and regulatory controls. Findings indicate that real-time checks by supervised agents can become more effective in making responsible choices, whereas calibrated and continuous checks and balances are indispensable.
References
[1]. Buckley, R.P., Zetzsche, D.A., Arner, D.W. and Tang, B.W., 2021. Regulating artificial intelligence in finance: Putting the human in the loop. Sydney Law Review, The, 43(1), pp.43-81.
[2]. Mthembu, E.C., 2022. Ethical AI-First Banking: Cloud-Powered Cyber Decision Infrastructure with Quantum Machine Learning and Agentic Negotiation Frameworks. International Journal of Engineering & Extended Technologies Research (IJEETR), 4(4), pp.5017-5021.
[3]. Fletcher, G.G.S. and Le, M.M., 2021. The future of AI accountability in the financial markets. Vand. J. Ent. & Tech. L., 24, p.289.
[4]. Johnson, K.N., 2019. Automating the risk of bias. Geo. Wash. L. Rev., 87, p.1214.
[5]. Ruiz, C.I.S., 2021. AI-Driven Software Development for Scalable IoT Hybrid Fuzzy WPM and TOPSIS Integration with Deep Learning and Particle Swarm Optimization in Agentic Negotiation Frameworks. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 4(5), pp.5570-5574.
[6]. Truby, J., Brown, R. and Dahdal, A., 2020. Banking on AI: mandating a proactive approach to AI regulation in the financial sector. Law and Financial Markets Review, 14(2), pp.110-120.
[7]. Iqbal, J. and Saleh, A., 2020. Artificial Intelligence–Driven Decision Support Systems For Smart Enterprises. International Research Journal of Advanced Science, 1(1), pp.1-11.
[8]. Zerilli, J., Knott, A., Maclaurin, J. and Gavaghan, C., 2019. Algorithmic Decision-Making and the Control Problem: J. Zerilli et al. Minds and Machines, 29(4), pp.555-578.
[9]. Ejeofobiri, C.K., Adelere, M.A. and Shonubi, J.A., 2022. Developing adaptive cybersecurity architectures using Zero Trust models and AI-powered threat detection algorithms. Int J Comput Appl Technol Res, 11(12), pp.607-621.
[10]. Kolyshkina, I. and Simoff, S., 2021. Interpretability of machine learning solutions in public healthcare: the CRISP-ML approach. Frontiers in big data, 4, p.660206.
[11]. Kumar, A., Sharma, S. and Mahdavi, M., 2021. Machine learning (Ml) technologies for digital credit scoring in rural finance: a literature review. Risks, 9(11), p.192.
[12]. Zhang-Zhang, Y., Rohlfer, S. and Rajasekera, J., 2020. An eco-systematic view of cross-sector fintech: The case of Alibaba and Tencent. Sustainability, 12(21), p.8907.
[13]. Ullah, I., Rios, A., Gala, V. and Mckeever, S., 2021. Explaining deep learning models for tabular data using layer-wise relevance propagation. Applied Sciences, 12(1), p.136.
[14]. Bekamiri, H., Ghasempour Ganji, S.F., Simonetti, B. and Seno, S.A.H., 2021. A new model to identify the reliability and trust of internet banking users using fuzzy theory and data-mining. Mathematics, 9(9), p.916.
[15]. Pu, R., Teresiene, D., Pieczulis, I., Kong, J. and Yue, X.G., 2021. The interaction between banking sector and financial technology companies: qualitative assessment—a case of Lithuania. Risks, 9(1), p.21.
[16]. Ramos Montesdeoca, M., Sanchez Medina, A.J. and Blazquez Santana, F., 2019. Research topics in accounting fraud in the 21st century: A state of the art. Sustainability, 11(6), p.1570.
[17]. Lahkani, M.J., Wang, S., Urbański, M. and Egorova, M., 2020. Sustainable B2B E-commerce and blockchain-based supply chain finance. Sustainability, 12(10), p.3968.
[18]. Bayram, O., Talay, I. and Feridun, M., 2022. Can FinTech promote sustainable finance? Policy lessons from the case of Turkey. Sustainability, 14(19), p.12414.
[19]. Zarrouk, H., El Ghak, T. and Bakhouche, A., 2021. Exploring economic and technological determinants of FinTech startups’ success and growth in the United Arab Emirates. Journal of Open Innovation: Technology, Market, and Complexity, 7(1), p.50.
[20]. Mao, D., Wang, F., Hao, Z. and Li, H., 2018. Credit evaluation system based on blockchain for multiple stakeholders in the food supply chain. International journal of environmental research and public health, 15(8), p.1627.
[21]. Tsiakas, K. and Murray-Rust, D., 2022, June. Using human-in-the-loop and explainable AI to envisage new future work practices. In Proceedings of the 15th international conference on PErvasive technologies related to assistive environments (pp. 588-594).
[22]. Methnani, L., Aler Tubella, A., Dignum, V. and Theodorou, A., 2021. Let me take over: Variable autonomy for meaningful human control. Frontiers in Artificial Intelligence, 4, p.737072.
[23]. Enarsson, T., Enqvist, L. and Naarttijärvi, M., 2022. Approaching the human in the loop–legal perspectives on hybrid human/algorithmic decision-making in three contexts. Information & Communications Technology Law, 31(1), pp.123-153.
[24]. Nakao, Y., Stumpf, S., Ahmed, S., Naseer, A. and Strappelli, L., 2022. Toward involving end-users in interactive human-in-the-loop AI fairness. ACM Transactions on Interactive Intelligent Systems (TiiS), 12(3), pp.1-30.
[25]. Hamrouni, B., Bourouis, A., Korichi, A. and Brahmi, M., 2021. Explainable ontology-based intelligent decision support system for business model design and sustainability. Sustainability, 13(17), p.9819.
[26]. Cabrera, D., Cubillos, C., Urra, E. and Mellado, R., 2020. Framework for incorporating artificial somatic markers in the decision-making of autonomous agents. Applied Sciences, 10(20), p.7361.
[27]. Reis, J., Santo, P. and Melão, N., 2020. Impact of artificial intelligence research on politics of the European Union member states: The case study of Portugal. Sustainability, 12(17), p.6708.
[28]. Amoako, G., Omari, P., Kumi, D.K., Agbemabiase, G.C. and Asamoah, G., 2021. Conceptual framework—artificial intelligence and better entrepreneurial decision-making: the influence of customer preference, industry benchmark, and employee involvement in an emerging market. Journal of Risk and Financial Management, 14(12), p.604.
[29]. Vakili, S.V., Ölçer, A.I. and Schönborn, A., 2021. Identification of shipyard priorities in a multi-criteria decision-making environment through a transdisciplinary energy management framework: a real case study for a Turkish shipyard. Journal of Marine Science and Engineering, 9(10), p.1132.
[30]. Yoo, S.K. and Kim, B.Y., 2018. A decision-making model for adopting a cloud computing system. Sustainability, 10(8), p.2952.
[31]. V. K. B. Parasaram, V. T. Bathini, S. K. Nalluri and A. H. Sannidhanam, "A Sustainable AI-Enabled Predictive Maintenance Framework for Smart Industrial Systems Using Industrial IoT Data," 2026 Third International Conference on Innovations in Cybersecurity and Data Science (ICICDS), Pathum Thani, Thailand, 2026, pp. 440-447, doi: 10.1109/ICICDS70526.2026.11604878.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Author
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
