Identify money laundering activity and proactively detect mule accounts before the funds are moved. Mule Account Detection can help mitigate financial, reputational, and regulatory risk.
Problem overview
Mule accounts play a critical role in the fraud supply chain infrastructure and are a mechanism to cash out fraudulent transactions, launder money, and support criminal operations. Money mules come in many forms, each with different goals and behaviors that require unique approaches to detect. In addition to AML for AO and ATO, BioCatch’s Mule Account Detection detects sold accounts, accomplices, and misled mules. These personas often go undetected with standard fraud detection measures.
Traditional transaction-monitoring solutions also tend to identify mules only after the critical moment of payment, wire, or transfer. According to a Forrester report on EFM and AML, key stakeholders have reported a drastic increase in global investigation time year over year. This has led to increased operational costs to investigate, report, and shutter money laundering accounts. Traditional solutions are simply not enough.
Learn how Mule Account Detection uses behavioral intelligence to proactively detect these accounts and unique personas before the critical moment.
Money mules on the rise
90 %+
Percentage of money mule transactions directly linked to cybercrime
78 %
Increase in money mule activity among persons under 21
33 %
Percentage of financial institutions that cite a lack of resources to control
mule activity
79 %
Percentage of confirmed mule accounts that were highly active 90 days prior to an incoming payment
How BioCatch detects mule accounts
Mule Account Detection is optimized to identify money laundering accounts by analyzing thousands of features during online banking sessions. The solution can adapt and react in real time based on the fraudster's behavior. Below are a few of the behavioral sectors our machine learning models observe.
High Data familiarity
The solution analyzes login activity as many mule accounts are often genuine account holders, therefore the data will be highly familiar.
Behavioral anomalies
The solution looks for anomalies from mouse activity, typing patterns, navigation preferences, and platform choice.
Activity trend changes
The solution monitors activity changes, such as frequent log-ins or password resets prior to an incoming payment.
The Emerging Case
for Proactive Mule Detection
Every new or undiscovered mule account creates multiple risks for financial institutions. There is a growing need for proactive and preventative technology to detect mule accounts due to changes in the reimbursement models. Mule Account Detection can help by detecting money laundering accounts before the payment has been sent.
Access the latest research to learn what leading banks expect for future rates of mule activity, current approaches to managing the problem, and how they are mobilizing to address it.
use cases (FRAML)
The account peddler
The accomplice
The misled mule
Identity theft