Money laundering and terrorism financing detection using neural networks and an abnormality indicator
This study proposes a comprehensive model that helps improve self-comparisons and group-comparisons for customers to detect suspicious transactions related to money laundering (ML) and terrorism financing (FT) in financial systems. The self-comparison is improved by establishing a more comprehensive...
| Autores: | , , |
|---|---|
| Formato: | artículo |
| Fecha de publicación: | 2021 |
| País: | España |
| Recursos: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/8075 |
| Acesso em linha: | https://hdl.handle.net/20.500.14352/8075 |
| Access Level: | acceso abierto |
| Palavra-chave: | Money laundering Financing of terrorism Unsupervised learning Detection Machine Learning. Dinero 5304.06 Dinero y Operaciones Bancarias |
| Resumo: | This study proposes a comprehensive model that helps improve self-comparisons and group-comparisons for customers to detect suspicious transactions related to money laundering (ML) and terrorism financing (FT) in financial systems. The self-comparison is improved by establishing a more comprehensive know your customer (KYC) policy, adding non-transactional characteristics to obtain a set of variables that can be classified into four categories: inherent, product, transactional, and geographic. The group-comparison involving the clustering process is improved by using an innovative transaction abnormality indicator, based on the variance of the variables. To illustrate the way this methodology works, random samples were extracted from the data warehouse of an important financial institution in Mexico. To train the algorithms, 26,751 and 3527 transactions and their features, involving natural and legal persons, respectively, were selected randomly from January 2020. To measure the prediction accuracy, test sets of 1000 and 600 transactions were selected randomly for natural and legal persons, respectively, from February 2020. The proposed model manages to decrease the proportion of false positives and increase accuracy when compared to the rule-based system. On reducing the false positive rate, the company’s costs for investigating suspicious customers also decrease significantly. |
|---|