Iguodala, Osarense Dorothy and Oyiborhoro, Aghogho (2025) AI-Powered Anti-Money Laundering (AML) and fraud detection - enhancing financial security through intelligent fraud detection. World Journal of Advanced Research and Reviews, 26 (2). pp. 3702-3714. ISSN 2581-9615
![WJARR-2025-0637.pdf [thumbnail of WJARR-2025-0637.pdf]](https://eprint.scholarsrepository.com/style/images/fileicons/text.png)
WJARR-2025-0637.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial Share Alike.
Abstract
The increasing sophistication of financial crimes, including money laundering and fraud, necessitates advanced technological solutions to enhance financial security. Artificial Intelligence (AI)-powered Anti-Money Laundering (AML) and fraud detection systems have emerged as transformative tools in the financial sector, enabling proactive threat identification and risk mitigation. This study explores the integration of AI techniques—such as machine learning (ML), deep learning, and natural language processing (NLP)—in detecting fraudulent activities and identifying suspicious transactions in real time. AI-driven AML frameworks leverage predictive analytics and anomaly detection models to enhance compliance with regulatory frameworks while reducing false positives. This research highlights key AI-based methodologies in fraud detection, including supervised and unsupervised learning models, neural networks, and reinforcement learning. Moreover, it examines the role of explainable AI (XAI) in improving transparency and trust in financial security operations. The integration of AI with blockchain technology is also discussed, showcasing its potential to enhance transaction traceability and prevent illicit activities. Despite its advantages, AI-driven AML systems face challenges, including data privacy concerns, adversarial attacks, and regulatory compliance issues. This study emphasizes the need for a balanced approach that combines AI innovation with ethical and legal considerations. By leveraging AI-powered AML and fraud detection, financial institutions can significantly improve their ability to combat financial crime, ensuring a more secure and resilient global financial ecosystem.
Item Type: | Article |
---|---|
Official URL: | https://doi.org/10.30574/wjarr.2025.26.2.0637 |
Uncontrolled Keywords: | AI-driven AML; Fraud detection; Machine learning; Financial security; Predictive analytics; Regulatory compliance |
Depositing User: | Editor WJARR |
Date Deposited: | 20 Aug 2025 11:45 |
Related URLs: | |
URI: | https://eprint.scholarsrepository.com/id/eprint/3551 |