Enhancing Anti-Money Laundering Effectiveness through AI-Enabled Detection of Cyber-Enabled Financial Crime: A Risk-Based Framework for U.S. Financial Institutions
Algora · 2026
DOI: 10.63084/algora.v3i1.110 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algora, 2026. Verfasst von Eseroghene Majomi.
Abstract (Originalsprache)
The rapid expansion of digital banking, mobile payment platforms, crypto currencies, and interconnected financial technologies has transformed the global financial ecosystem while simultaneously increasing the sophistication and frequency of cyber-enabled financial crimes. U.S. financial institutions are confronted with increasingly complex money laundering schemes that exploit online payment systems, synthetic identities, ransom ware proceeds, phishing attacks, business email compromise, and cross-border digital transactions. Conventional anti-money laundering (AML) systems, which primarily rely on static rule-based monitoring, often struggle to identify evolving criminal behaviors, resulting in high false-positive rates, delayed investigations, and inefficient allocation of compliance resources. These limitations have intensified the need for intelligent, adaptive, and risk-based detection mechanisms capable of identifying suspicious financial activities in real time (Financial Action Task Force [FATF], 2023). Artificial intelligence (AI), particularly machine learning, deep learning, natural language processing, and graph analytics, has emerged as a transformative technology for strengthening AML capabilities by improving anomaly detection, behavioral analysis, predictive risk assessment, and network relationship identification while supporting regulatory compliance and operational efficiency. This study proposes an AI-enabled risk-based framework designed to enhance the effectiveness of AML programs within U.S. financial institutions by integrating intelligent transaction monitoring, dynamic customer risk profiling, explainable AI, and continuous governance mechanisms. The framework emphasizes transparency, regulatory accountability, and human oversight to ensure that AI-assisted decisions remain interpretable, auditable, and aligned with evolving compliance expectations. It further demonstrates how AI can improve the early detection of cyber-enabled financial crime, reduce false-positive alerts, optimize investigative workflows, and strengthen institutional resilience against emerging financial threats. By combining advanced analytical techniques with a comprehensive governance structure, the proposed framework contributes to both academic knowledge and professional practice by offering a practical roadmap for modernizing AML systems in an increasingly digital financial environment. The findings are expected to assist financial institutions, regulators, policymakers, and technology developers in implementing robust, risk-based, and AI-driven strategies that improve financial integrity, support regulatory compliance, and enhance the overall effectiveness of anti-money laundering initiatives in the United States.
Zitieren
APA
Majomi, E. (2026). Enhancing Anti-Money Laundering Effectiveness through AI-Enabled Detection of Cyber-Enabled Financial Crime: A Risk-Based Framework for U.S. Financial Institutions. Algora. https://doi.org/10.63084/algora.v3i1.110
Vancouver
Majomi E. Enhancing Anti-Money Laundering Effectiveness through AI-Enabled Detection of Cyber-Enabled Financial Crime: A Risk-Based Framework for U.S. Financial Institutions. Algora. 2026. doi:10.63084/algora.v3i1.110
BibTeX
@article{Majomi2026,
author = {Majomi, Eseroghene},
title = {Enhancing Anti-Money Laundering Effectiveness through AI-Enabled Detection of Cyber-Enabled Financial Crime: A Risk-Based Framework for U.S. Financial Institutions},
journal = {Algora},
year = {2026},
doi = {10.63084/algora.v3i1.110}
}
EUVIMED