Applying Ensemble Learning for Detecting Trade-Based Money Laundering in International Channels

Abstrak

The increasing complexity and volume of banking transactions have made manual investigative audits highly time-consuming and prone to human error. This study explores the utilization of Artificial Intelligence (AI) to automate investigative auditing processes in the banking sector. The proposed approach employs machine learning algorithms to analyze transactional patterns and detect potential fraud with greater speed and precision. By automating data analysis, the system enhances efficiency, reduces operational workload, and improves the consistency of audit outcomes. The implementation phase involves training various machine learning models to identify abnormal transaction behaviors that may indicate internal or external fraud. Comparative analysis shows that the AI-based audit system significantly outperforms traditional manual audits in terms of detection accuracy and response time. Furthermore, the AI system minimizes false positives and enables real-time fraud monitoring, providing auditors with a powerful tool to enhance decision-making. The study concludes that integrating AI into internal audit infrastructures represents a strategic advancement toward smarter and more reliable auditing systems. Future research should focus on improving model interpretability to ensure transparency and on developing hybrid models that combine human expertise with AI efficiency. This integration marks an important step toward transforming the auditing landscape in the era of digital banking.

Identifier

• DOI: https://doi.org/10.70062/jiafc.v1i3.236
• OpenAlex: https://openalex.org/W7124738463