International Journal of Education and Management Engineering (IJEME)
IJEME Vol. 16, No. 2, 8 Apr. 2026
Cover page and Table of Contents: PDF (size: 553KB)
Adaptive AI-Driven Anomaly Detection Framework for Identity & Access Management in Financial Technology Systems
PDF (553KB), PP.1-14
Views: 0 Downloads: 0
Author(s)
Index Terms
Identity and Access Management (IAM), Anomaly Detection, Artificial Intelligence, Machine Learning, Deep Learning, Autoencoder, Random Forest, Financial Technology Security, Insider Threat Detection, Cybersecurity
Abstract
Identity and Access Management (IAM) is critical for securing digital assets, particularly in financial technology (FinTech) systems, where unauthorized access can lead to significant financial losses. Three formal research questions guide this work: (RQ1) Do AI-driven models statistically significantly outperform traditional rule-based IAM systems in anomaly detection accuracy? (RQ2) Which AI model best balances precision and recall for real-time insider-threat detection under class-imbalanced IAM log conditions? (RQ3) Are the observed performance gains robust and stable across cross-validated experimental folds? This study evaluates the performance of AI-driven anomaly detection models, including autoencoders, random forests, and support vector machines, in detecting unusual user activities and potential insider threats. The Autoencoder model achieved the highest overall accuracy of 94.2% (+/- 0.8% across five-fold cross-validation) with a precision of 92.8% and recall of 91.5%. The Random Forest attained a slightly lower accuracy (92.5%) but excelled in recall (93.2%), highlighting its strength in identifying actual malicious activities. Compared to traditional rule-based IAM methods, which achieved only 78.4% accuracy, AI models significantly improved anomaly detection, particularly for subtle or previously unseen threats. McNemar's tests confirm that all accuracy improvements over the baseline are statistically significant (p < 0.001). The Autoencoder also demonstrated the lowest latency (120 ms), making it suitable for real-time deployment. These results confirm that AI-enhanced IAM systems can effectively strengthen security and operational efficiency in FinTech environments, within the scope of the simulated and publicly available datasets employed in this study.
Cite This Paper
Karimulla Syed, Elijah Falode, Adeel Shaik Muhammad, "Adaptive AI-Driven Anomaly Detection Framework for Identity & Access Management in Financial Technology Systems", International Journal of Education and Management Engineering (IJEME), Vol.16, No.2, pp. 1-14, 2026. DOI:10.5815/ijeme.2026.02.01
Reference
[1][summitroute2020] SummitRoute, "Public Dataset of CloudTrail Logs from Flaws.Cloud," 2020. [Online]. Available: https://summitroute.com/downloads/flaws_cloudtrail_logs.tar [Accessed: 15-Nov-2025].
[2][kaggle2023] Das Group, "Login Data Set for Risk-Based Authentication," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/dasgroup/rba-dataset [Accessed: 15-Nov-2025].
[3][cert2020] B. Lindauer, "Insider Threat Test Dataset," Carnegie Mellon University, 2020. Dataset. doi: 10.1184/R1/12841247.v1. [Online]. Available: https://doi.org/10.1184/R1/12841247.v1 [Accessed: 15-Nov-2025].
[4][cert_glasser2013] J. Glasser and B. Lindauer, "Bridging the Gap: A Pragmatic Approach to Generating Insider Threat Data," in Proc. 2013 IEEE Security and Privacy Workshops (SPW), San Francisco, CA, USA, 2013, pp. 98-104. doi: 10.1109/SPW.2013.37. [Online]. Available: https://ieeexplore.ieee.org/document/6565236
[5]F. Chad, "AI-Driven Identity and Access Management for Cloud Security," ResearchGate Preprint, vol. 3, no. 1, pp. 1-15, 2025. [Online]. Available: https://www.researchgate.net/publication/389437988 [Note: Grey literature; no formal DOI assigned at time of submission].
[6]S. Selling, "Advancing Identity and Access Management with Artificial Intelligence for Anomaly Detection: A Proof of Concept Implementation Study," KTH Diva Portal, 2024. diva2:1943652. [Online]. Available: https://www.diva-portal.org/smash/get/diva2:1943652/FULLTEXT02
[7]S. Thorat, D. I. Navalgund, L. K. Gautam, and A. Saini, "Collaborative AI Solutions for Identity and Access Management," in Smart Innovation, Systems and Technologies, Springer, 2024, pp. 98-113. doi: 10.1007/978-981-96-2124-8_41. [Online]. Available: https://link.springer.com/chapter/10.1007/978-981-96-2124-8_41
[8]S. Kumar and R. Mehta, "AI-Enhanced Identity and Access Management: A Machine Learning Approach to Zero Trust Security," The Computertech, vol. 4, no. 2, pp. 123-134, 2019. [Online]. Available: http://www.yuktabpublisher.com/index.php/TCT/article/view/163
[9]Z. Sai'd, "Explainable AI (XAI) in Identity Access Management: Bridging Trust and Transparency in User Authentication," Authorea Preprints, 2025. doi: 10.22541/au.175207868.84087923. [Online]. Available: https://www.authorea.com/doi/full/10.22541/au.175207868.84087923
[10]A. Singh, "AI-Driven Anomaly Detection for Advanced Threat Detection," IEEE Transactions on Dependable and Secure Computing, 2023. [Online]. Available: https://ieeexplore.ieee.org/search/searchresult.jsp?queryText=AI-Driven+Anomaly+Detection+Advanced+Threat+Detection+Singh+2023
[11]Y. Sharma, "The Role of AI and Machine Learning in Identity Governance," ResearchGate, vol. 7, no. 4, pp. 112-125, 2024. [Online]. Available: https://www.researchgate.net/publication/392834516 [Note: Preprint; no formal DOI assigned at time of submission].
[12]T. Singhal and S. Balakrishnan, "AI-Driven Identity Access Management and Blockchain: Enhancing Security with Machine Learning," 2023. [Online]. Available: https://scholar.google.com/scholar?q=Singhal+Balakrishnan+AI+Identity+Access+Management+Blockchain+2023
[13]R. Hegde, "AI-Driven Identity Access Management for Enhanced Cloud Security," iMedPub Journals, 2025. doi: 10.1016/j.imed.2024.09.003. [Online]. Available: https://doi.org/10.1016/j.imed.2024.09.003
[14]J. Prakash and A. Ali, "Real-Time Anomaly Detection in Identity Access Management Systems," International Journal of Computer Science and Network Security, vol. 9, no. 1, pp. 20-30, 2024.
[15]S. Kumar, "Application of Deep Learning in Identity and Access Management Systems," 2025. [Online]. Available: https://www.academia.edu/papers/Deep_Learning_Identity_Access_Management_Systems
[16]A. Singh and S. V. Reddy, "AI-Powered Risk Management for Identity and Access Control in Cloud Systems," Journal of Cloud Computing, vol. 6, no. 3, pp. 95-110, 2024.
[17]R. Rajak, N. Kumaresh, and S. V. Sankari, "AI-Driven Anomaly Detection for Secure Identity and Access Management in Cloud Platform," Global Journal of Computer Science and Technology, vol. 5, no. 3, pp. 88-101, 2024. [Online]. Available: https://www.semanticscholar.org/paper/AI-Driven-Anomaly-Detection-for-Secure-Identity-and-/15a9b6ddba7764c9229a1cb01f16217e1b5933cb
[18]D. E. O'Leary, "AI-Powered Identity and Access Management," International Journal of Advanced Research in Computer Science and Technology (IJARCST), vol. 8, no. 5, pp. 12907-12919, 2025. [Online]. Available: https://ijarcst.org/index.php/ijarcst/article/download/171/164
[19]J. Vegas and C. Llamas, "Opportunities and Challenges of Artificial Intelligence Applied to Identity and Access Management in Industrial Environments," Multimedia Tools and Applications, Springer, 2024. doi: 10.1007/s11042-024-01687-5. [Online]. Available: https://link.springer.com/article/10.1007/s11042-024-01687-5
[20]S. Aboukadri, A. Ouaddah, and A. Mezrioui, "Machine Learning in Identity and Access Management Systems: Survey and Deep Dive," Computers and Security, Elsevier, vol. 139, Article 103733, 2024. doi: 10.1016/j.cose.2024.103729. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0167404824000300
[21]C. Singh, "IAM Identity Access Management -- Importance in Modern Digital Business," European Journal of Engineering and Technology Research, vol. 4, no. 3, pp. 123-134, 2023. doi: 10.24018/ejeng.2023.8.3.3074. [Online]. Available: https://www.ej-eng.org/index.php/ejeng/article/view/3074
[22]B. Rajak, N. Kumaresh, and S. V. Sankari, "AI-Driven Anomaly Detection for Secure Identity and Access Management in Cloud Platform," Global Journal of Computer Science and Technology: E Network, Web and Security, vol. 7, no. 3, pp. 45-58,
[23]2024. [Online]. Available: https://www.semanticscholar.org/paper/AI-Driven-Anomaly-Detection-for-Secure-Identity-and-/15a9b6ddba7764c9229a1cb01f16217e1b5933cb
[24]A. Thomas and D. Alexander, "AI-Driven Anomaly Detection for Insider Threat Prevention in Identity and Access Management (IAM) Systems," International Journal of Advanced Engineering Technologies and Innovations, vol. 5, no. 3, pp. 123-135, 2023. [Online]. Available: https://www.researchgate.net/publication/393784721
[25]S. Vitla, "The Future of Identity and Access Management: Leveraging AI," Journal of Cybersecurity and Telecommunications Systems, vol. 6, no. 1, pp. 56-65, 2024. [Online]. Available: https://al-kindipublishers.org/index.php/jcsts/article/view/8619
[26]R. Chinni, "Evaluating Adaptive Access Policies for Zero Trust Architectures in Modern Cybersecurity Environments," in Proc. 2025 International Conference on Computing Technologies and Data Communication (ICCTDC), IEEE, 2025, pp. 1-10.
[27]S. M. Adeel, "AI-Powered Cybersecurity Compliance: Bridging Regulations and Innovation," Journal of Current Trends in Computer Science Research, vol. 4, no. 3, pp. 01-23, 2025. [Online]. Available: https://www.opastpublishers.com/open-access-articles/aipowered-cybersecurity-compliance-bridging-regulations-and-innovation.pdf