Global resources suffer a cost of around $1.6 trillion per year due to money laundering efforts across the world, according to the UN United States’ banks spend between 0.4% and 2.4% of their total operating expenses trying to prevent fraud and money laundering. Additionally, millions are being spent on compliance with the Treasury Department’s Customer Due Diligence (CDD) Rule.
This example illustrates how SAS Event Stream Processing (ESP) can detect possible fraud and money laundering transactions without the use of advanced analytics. The detection is performed using data comparison and analysis with rules, predominantly in sliding, temporal windows. This allows ESP to look for patterns in specific time windows.
There are three fraud and anti-money laundering rules associated with this example:
- Four consecutive “cash out” transactions by the same customer in a 10-minute span. If this occurs ESP issues a decline message.
- Many to one fund transfers. If three or more distinct customers are sending transactions to the same beneficiary in a one-day period, ESP issues a decline message
- Transactions originating or terminating from a high-risk location. If a beneficiary name is flagged after being compared to a restricted list, ESP issues an on-hold message indicating further investigation is needed.
The Streaming Fraud and Anti-Money Laundering Simple Example GitHub page has all you need to execute this example yourself. Be sure to check it out.
