A Hybrid Modeling Approach For Detecting Money Laundering In Banking Sectors

Abstract

Money laundering poses a significant challenge to
financial institutions, enabling illicit activities such as
fraud, corruption, and terrorism financing. Traditional
rule-based systems and statistical methods often fail
to detect complex laundering schemes due to their
adaptability and evolving nature. To address these
limitations, this paper proposes a hybrid modeling
approach that integrates machine learning (ML)
techniques with rule-based methods to enhance
money laundering detection in banking sectors. The
hybrid model leverages supervised and unsupervised
ML algorithms alongside predefined rules to improve
the identification of suspicious transactions, reducing
false positives and enhancing detection accuracy. Our
approach combines anomaly detection, clustering
techniques, and predictive analytics to analyze
transactional data dynamically. By incorporating
behavioral profiling and real-time monitoring, the
model adapts to emerging laundering patterns while
maintaining regulatory compliance. Experimental
results demonstrate that the hybrid framework
outperforms conventional detection systems in terms
of precision, recall, and adaptability. This research
contributes to financial security by providing a robust
and scalable solution for combating money
laundering, ultimately strengthening the resilience of
banking institutions against financial crimes.