ork.AI
Transaction monitoring (TM) is a process that identifies suspicious behavior indicating money laundering or other financial crimes that occur after a transaction is made by a person or an organization. It is a requirement for anti-money laundering/countering the financing of terrorism (AML/CFT) programs globally and is a critical tool for fighting financial crime.
While it’s a required component for AML, it can be a difficult compliance obligation for banks that manually review millions of transaction monitoring alerts each month with the majority of those alerts being non-suspicious. These monitoring programs focused on suspicious activity take a lot of time, require large teams of people, and cost a lot of money.
False Positive Burden
Many FIs are still solely relying on traditional rules-based transaction monitoring systems. To ensure they are monitoring transactions as efficiently and effectively as possible, they cast a wide net of rules to not miss anything, which generates high alert volumes and exceptionally high false-positive rates.
False positives in transaction monitoring occur when a normal transaction is mistakenly flagged as suspicious and risky. Due to the parameters of transaction monitoring and screening measures, some normal customer behaviors that aren’t suspicious may look like they are. For instance, a customer who makes many bank transfers from different banks to different destinations on the same day may trigger an AML alert even though their transactional behavior is legitimate for business reasons.
“Transaction monitoring is a time-consuming and expensive, yet critical component of AML compliance,” explains Art Mueller, WorkFusion’s Vice President of Financial Crime. “Every day, teams of analysts within banks review large numbers of alerts associated with transactions, patterns or behaviors that flag as potentially suspicious for money laundering or other financial crime. Analysts must determine whether these alerts are false positives (which typically 90-95% are) or truly suspicious activity.”
Not Enough Time or People
Transaction monitoring is based on comparing transactions that have occurred against deployed scenarios to generate an alert. These alerts will be generated daily, weekly, or monthly post-transaction. So, organizations are not trying to interdict the payment or transaction, they’re trying to determine if an alert needs to be escalated further and if they need to file a suspicious activity report (SAR).
These TM alerts are typically worked on a 30/30/30 schedule. This means it takes 30 days to review an alert; 30 days to work an alert that has been escalated to a case; and 30 days to file a SAR once a decision to file has been made. Many banks that work on this 90-day cycle, especially those that generate a lot of alerts, may not have the manpower to do the work and end up with backlogs.
Too Much Busy Work
TM analysts tend to be hunter-gatherers who spend a large part of their time doing busy work rather than leveraging their true talent for fighting financial crime. Upwards of 80-85% of the work they perform is spent tracking down information, no matter what the alert is. With so many places to gather information, from various systems (we’ve heard upwards of 30 systems) to relationship managers who can provide information, TM analysts are doing a lot of different tasks just to pull together everything before they can even analyze an alert. From there, they need to identify the information that’s required to support an investigation. As a result, TM analysts are doing a lot of time-consuming and laborious work as part of an alert, even for a simple alert.
Introducing Issac: an AI Transaction Monitoring Investigator
For a successful transaction monitoring program, FIs need assistance in aggregating the vast amount of data and supporting documentation in case management systems, enriching investigations with data from third-party sources and internal tools, analyzing for links and relationships between multiple data points, detecting anomalies for unusual patterns and outliers, and performing expectation analysis to compare actual versus expected activity, as well as sorting through the tremendous amount of false positives.
WorkFusion has just rolled out its newest AI Digital Worker, Isaac, an AI Transaction Monitoring Investigator to help overcome these common issues. Isaac assists with TM alert management by using machine learning capabilities to work first-level alerts. He auto-escalates alerts that are likely to require investigation and closes alerts that are non-suspicious with supporting narrative and documentation, allowing your analysts to focus on the highest-risk activity.
Overcome TM challenges with Issac as your AI Transaction Monitoring Investigator:
- Automate L1 Review of TM alerts to Alleviate False Positives
Isaac auto-clears non-suspicious TM alerts and auto-escalates more suspicious alerts for deeper review, allowing investigators to focus on higher-value investigative work. - Turn Analysts from Authors to Editors
Using the dossier that Isaac compiles, analysts can easily read through the data and narrative, as opposed to the time-consuming tasks of searching and compiling data. - Mitigate Risk
Reduce risk by enabling earlier and faster escalation of suspicious alerts. Automated L1 review saves time and the cost of human analyst review, reducing and eliminating manual touchpoints based on risk threshold. - Improve Compliance
Isaac provides documented, transparent, human-readable decisions of the alert review process with a confidence threshold for regulators.
Isaac supports common BSA transaction monitoring scenarios that generate a high volume of alerts, such as:
- Structuring
- Excessive funds transfers/movement of funds/patterns of funds transfers
- Unexpected account usage/behavior
- High-risk factors
- Use of dormant accounts
Hear more about how our AI Digital Workers are helping fight financial crime and more details about Issac from our CTO, Peter Cousins, in the video above or request a demo.