Machine Learning Methodologies Against Money Laundering in Non-Banking Correspondents

Guevara, Javier; Garcia-Bedoya, Olmer; Granados, Óscar

doi:10.1007/978-3-030-61702-8_6

Cited by 10 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can analyze transaction data and identify unusual patterns that may indicate fraudulent activity. These algorithms can flag potentially fraudulent transactions in real-time, preventing losses and enhancing the security of financial systems (Guevara, Garcia-Bedoya, & Granados, 2020;Lokanan, 2022).…”

Section: Fraud Detectionmentioning

confidence: 99%

Harnessing Ai for Africa's Financial Fortification: A Review

Augustine Lottu,

Mobolaji Abioye,

Naomi Oguntoyinbo

et al. 2023

Bus.org.soci

View full text Add to dashboard Cite

Africa’s financial landscape presents a complex tapestry characterized by adversity and opportunity. It is home to a significant portion of the world’s unbanked and underbanked population, with millions still lacking access to fundamental financial services. However, amid these challenges, Africa also boasts a burgeoning tech-savvy population, a growing number of innovative fintech startups, and governments increasingly recognizing the pivotal role of financial inclusion in sustainable development. This dynamic interplay between adversity and opportunity defines Africa’s financial sector, shaping its trajectory during this economic and technological transformation era. This paper explores the challenges and opportunities of adopting Artificial Intelligence (AI) within the African financial sector. The study researches the current landscape, underlining key statistics such as the substantial percentage of African unbanked individuals. It also identifies significant barriers to AI adoption, such as infrastructure limitations, data quality issues, and regulatory ambiguities. To address these challenges effectively, the paper proposes actionable recommendations targeted at policymakers, financial institutions, and stakeholders. To maximize AI’s potential for transforming the African financial sector, strategies for infrastructure development, data quality enhancement, regulatory clarity, skills development, and the ethical deployment of AI are discussed. This paper highlights the challenges and underscores AI’s immense potential for financial inclusion and economic growth in Africa.

show abstract

Section: Fraud Detectionmentioning

confidence: 99%

Harnessing Ai for Africa's Financial Fortification: A Review

Augustine Lottu,

Mobolaji Abioye,

Naomi Oguntoyinbo

et al. 2023

Bus.org.soci

View full text Add to dashboard Cite

show abstract

“…In the AML domain, a recent research trend has demonstrated the effectiveness of the application of Isolation Forests and Support Vector Machines to the detection of money laundering patterns [20], [21].…”

Section: A Unsupervised Learningmentioning

confidence: 99%

“…As pointed out in Section III, an unsupervised method is essential to detect new anomalous patterns never seen before. We decided to use Isolation Forest [20], [21] due to its high performance in detecting outliers even if they are present in Algorithm 1 Pseudocode of Amaretto's approach: L is the set of the feedback received by the fraud analyst; U is the set of transactions; mod is the machine learning model; sup stands for supervised; unsup stands for unsupervised; strat is the selection strategy; K denotes the top-K high-level vectors in the ranking; T denotes the set of time windows. )…”

Section: Unsupervised Modulementioning

confidence: 99%

See 1 more Smart Citation

Amaretto: An Active Learning Framework for Money Laundering Detection

et al. 2022

View full text Add to dashboard Cite

Monitoring financial transactions is a critical Anti-Money Laundering (AML) obligation for financial institutions. In recent years, machine learning-based transaction monitoring systems have successfully complemented traditional rule-based systems to reduce the high number of false positives and the effort needed to review all the alerts manually. Unfortunately, machine learning-based solutions also have disadvantages: while unsupervised models can detect novel fraudulent patterns, they are usually characterized by a high number of false alarms; supervised models, instead, usually offers a higher detection rate but require a large amount of labeled data to achieve such performance. In this paper, we present Amaretto, an active learning framework for money laundering detection that combines unsupervised and supervised learning techniques to support the transaction monitoring processes by improving the detection performance and reducing the fraud management costs. Amaretto exploits novel selection strategies to target a subset of transactions for investigation, making more efficient use of the feedback provided by the analyst. We perform the experimental evaluation on a synthetic dataset provided by the industrial partner, which simulates the profiles of clients trading in international capital markets. We show that Amaretto outperforms state-of-the-art solutions by reducing money laundering risk and improving detection performance. In particular, we compare state-of-the-art unsupervised and supervised techniques commonly used in the AML domain with the ones implemented in this work. We show that the Isolation and Random Forests of Amaretto perform best in the task under analysis, with an AUROC of 0.9 for the first (20% better on average) and a detection rate of 0.793 for the second (30% better on average). In addition, both methods are characterized by a lower costs computed in terms of the daily number of transactions to be examined and the number of false positives and negatives. Finally, we compare Amaretto against a state-of-the-art active learning fraud detection system, achieving better detection performances and lower costs in all the scenarios under analysis. Worth mentioning, Amaretto improves the detection rate up to 50% and reduces the overall cost by 20% in the most realistic scenario under analysis.

show abstract

Graph Contrastive Pre-training for Anti-money Laundering

Lu,

Wang

2024

Int J Comput Intell Syst

View full text Add to dashboard Cite

Machine Learning Methodologies Against Money Laundering in Non-Banking Correspondents

Cited by 10 publications

References 28 publications

Harnessing Ai for Africa's Financial Fortification: A Review

Harnessing Ai for Africa's Financial Fortification: A Review

Amaretto: An Active Learning Framework for Money Laundering Detection

Graph Contrastive Pre-training for Anti-money Laundering

Contact Info

Product

Resources

About