How to reduce false positives in sanctions screening

How to reduce false positives in sanctions screening

Do false positives make up a significant portion of your sanctions screening alerts?

Sanctions screening is an increasing priority for organisations. However, as anti-money laundering (AML) regulations become increasingly stringent, many screening systems and manual processes cannot keep pace, causing false positives to rise.

False positives are significant cost and efficiency drains, demanding time and resources that compliance departments don’t have. Organisations need to make it a priority to reduce false positives to maximise compliance efficiencies.

But there’s a catch.

Adjusting screening measures to reduce false positives could result in AML compliance penalties and increase the risk of financial criminals slipping through the cracks.

Therefore, organisations need to find the balance between reducing false positives while ensuring sanctions screening is as effective and compliant as possible.


What is a false positive?

A false positive is where the screening system flags a customer or entity as suspicious even though they may be innocent.

There are many causes of false positives. For example, a common cause is the diversity of naming conventions worldwide. This can result in different customers having very similar names, especially in Asian and Arabic cultures, which can lead to screening systems incorrectly matching them to names on sanctions lists.

Another cause is entities with similar names. There’s a long list of words that are popular in entity names, such as Global, Holdings, Solutions, and Digital. This can cause false matches on watchlists.


Reducing false positives - a compliance priority

False positives represent a significant compliance challenge for organisations working to comply with AML regulations.

Every false positive alert needs to be scrutinised by the AML compliance team, which takes resources away from analysing actual positive alerts.

False positives also create negative customer experiences. While alerts are analysed, customer onboarding is paused, transactions are stopped, and customers are prevented from accessing products and services. This results in friction and frustration, even leading to the loss of customers.

However, organisations cannot risk reducing the sensitivity of their sanctions screening measures. Fail to meet their regulatory obligations and the potential financial, reputational and crime risks are substantial.

Organisations should prioritise  their approach to reduce false positives while maintaining the accuracy and effectiveness of AML sanctions screening.


How to reduce false positives

Though it may not be possible to completely eliminate false positives, organisations can implement measures to reduce false positives:

1. Implement automated AML compliance technology

Automated AML compliance technology is designed to overcome the challenge of false positives while ensuring continued compliance.

Some legacy systems do not take into account the specific context of the match. For example, an individual’s name may be matched against the name of a sanctioned entity. They may use basic algorithms that do not consider the context of the entity or language and do not reflect the risk profile, which can lead to higher rates of false positives.

GBG’s Compliance Platform uses machine learning technology to draw on previously collected data, leverage the available context, and learn from past decisions to respond more effectively and accurately.

Data matching algorithms can be tailored to compare names, addresses, country, business names, and other identity attributes. Fuzzy matching detects near-matches in addition to exact matches while also having the ability to do phonetic-based matching. It also provides the flexibility to filter out matches based on date of birth and geography.

These are just some of the features that help improve the accuracy of matches and reduce the number of false positives.

2. Capture data in a structured way

Sanctions screening involves comparing vast amounts of data from various sources against sanctions lists to identify potential matches. However, data is not always collected in a structured way. Relying on this unstructured, unclear data can lead to a high rate of false positives.

The more confusing the data, the more challenging it is to discern false positives from true positive matches.

By rethinking the data capture process and structuring collected data clearly, organisations can improve their false positive rates.

3. Capture relevant customer data

The more relevant data an organisation has on a customer, the more complete their profile and the lower the risk of false positives.

For example, you could exclude individuals by using their date of birth, passport number or by checking their photo provided during the Know Your Customer (KYC) process.

It’s critical to ensure the customers’ identifying data held by the company is not only adequate, but up to date.

4. Continuously review your AML compliance

AML compliance is a continuous process. Organisations must focus on continually adapting and improving AML measures as new regulations are introduced, and new risks emerge.

Depending on changes in the landscape, it may be possible to adjust some sanction screening measures and therefore, reduce the false positive rates in a safe and controlled manner.


How GBG Compliance Platform reduces false positives

GBG’s Compliance Platform is the leading global fraud and AML service that automates AML compliance, sanctions screening and transaction monitoring in one platform. The Compliance Platform uses over 350 lists for global watchlist and sanctions screening. You can choose which lists you want enabled, what fuzzy matching you want per list and how often screening happens. Configure automated rules and matching technology based on your risk appetite or profile to reduce false positives while staying compliant.

Advanced features include:

  • List configuration: Enable different lists and thresholds based on customer geography, product type or risk.
  • Data Matching Algorithms: Algorithms are tailored to compare names, addresses, countries, business names, etc.
  • Configurable Fuzzy Matching: Fuzzy matching detects near-matches and exact matches with the ability to do phonetic-based matching. You can filter out matches based on date of birth and geography.
  • Continuous Monitoring: Define intervals at which a group of customers or all active users should be re-screened against sanctions lists.

Learn more about how GBG can help you reduce false positives and protect your customers and business against financial crime. Contact us to talk to an expert.

Sign up for more expert insight

Hear from us when we launch new research, guides and reports.