How Machine Learning Is Helping Financial Institutions Tackle Terrorist Funding

Daesh is an organization on the run internationally. No longer able to stage large-scale attacks, the group has resorted to covertly employing individuals, or small groups, to carry out terroristic misdeeds. The employ of small cells and lone operatives makes it difficult for law enforcement to identify and stop attacks in advance — and it also means tracking the path of their funds internationally is exceedingly tricky. While banks have long used anti-money laundering systems to flag suspicious activity, in the aftermath 9/11, those tools have been focused on catching terror-related transactions, too. However, with small sums now flowing from the group to individuals the world over, financial institutions are ill-equipped to the task of spotting the flow of cash. For instance, if the software spots a seven-figure transfer of funds from Florida to Colombia, it will flag it automatically as a drug and/or money-laundering transaction. However, in the present milieu, these tools are barely effective, as there are too many rules and possibilities to consider, and the small transactions a terrorist in hiding makes might not raise the requisite red flags. As a result, banks are increasingly turning to machine learning to mine their internal data and find anomalies that might otherwise go unnoticed. The discipline is still in its infancy as of 2017, but regulatory experts have high hopes for the potential of these tools — after all, machines are able to consider multiple additional data…

Link to Full Article: How Machine Learning Is Helping Financial Institutions Tackle Terrorist Funding

Pin It on Pinterest

Share This