false positives why you need to be aware of them in aml


False positives are always an issue for a financial institution’s Money Laundering Reporting Officer (MLRO). The MLRO has to spend substantial amounts of time and money investigating every client record that matches a name on a risk, sanction, or politically exposed person (PEP) register. Although institutions may want to change their rules for identifying matches, they’d end up helping more criminals launder money. Here’s why, and what financial institutions can do about it.

Inverse Relationship Between False Positives and False Negatives

If financial institutions tightened the rules on matching client names with risk, sanction or PEP registers, it would result in more false negatives. False negatives would let criminals access the financial system and continue laundering money. As a result, the MLRO and the institution may be assessed fines for their actions.

Need for Various Screening Technologies

Utilizing multiple screening technologies helps decrease false positives in AML. Here are a few of them.

A match key is an alpha-numeric grouping that is created from a complete record, often incorporating key elements like a name and postcode. Although match keys alone are ineffective for AML objectives, more sophisticated match keys may be used for grouping records for detailed comparison with fuzzy techniques.

Fuzzy techniques allow identification of inexact matches. For example, matching “Elizabeth” and “Elisabeth” involves fuzzy techniques.

Edit distance compares the number of character differences between two fields and determines how many edits/character changes must be made to one record to make it match the other record. Identical names have an edit distance score of 0, whereas similar names deliver a low score. For example, matching “Elizabeth” and “Elisabeth” results in a score of 1 and is typically considered a positive match.

The equivalence algorithm utilizes reference data for identifying pairs of records that are logically equivalent. For example, “Elizabeth” matches with “Elisa,” “Elsa,” “Beth,” “Betty,” and “Elisabeth.”

By implementing different screening technologies, the number of false positives and false negatives will be reduced. Additional attention may be focused on the greatest areas of risk.

Steps for Reducing False Positives

There are multiple ways to reduce the number of false positives that pop up during the screening process. Separate information from different fields by creating discrete entity types so that an individual’s name doesn’t match with an organization’s name that may be on a watch list. Use varying data types, such as passport numbers, for adding context to the screening process. Avoid using place names in a country, as they can be applied only to that country’s programs. In addition, financial institutions may include standardized code words at the start of each line of SWIFT payment instruction to keep related data together.

It’s important that you’re aware of false positives as a means of helping to prevent money laundering. For additional help with AML solutions, contact the recruiters at CarterWill Search & Flex today.


Leave a Reply