Money laundering and terrorism financing detection using neural networks and an abnormality indicator

作者：

Highlights：

• The inclusion of non-transactional variables improves the self-comparison.

• The indicator of abnormality improves the group-comparison.

• The proposed model manages to decrease the proportion of false positives.

• The developed system manages to increase the accuracy of prediction.

摘要

•The inclusion of non-transactional variables improves the self-comparison.•The indicator of abnormality improves the group-comparison.•The proposed model manages to decrease the proportion of false positives.•The developed system manages to increase the accuracy of prediction.

论文关键词：Money laundering,Financing of terrorism,Unsupervised learning,Detection,Machine Learning

论文评审过程：Received 7 August 2020, Revised 17 November 2020, Accepted 5 December 2020, Available online 11 December 2020, Version of Record 24 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114470