Existing screening technology is unable to keep pace with the demand for instant payments and is fraught with challenges around high volumes of false positives.
The fight against financial crime is not one that banks can win with their current technology and strategies. NextGen Client Screening is about maximising operational efficiencies through automation and configuration, to ensure FCC teams are focused on truly risk activity. What are the main challenges in sanctions screening and how does NextGen screening overcome them?
The biggest sanctions screening challenges
Most financial institutions using legacy technology are facing three main screening challenges:
- Instant payments growth
- Non-cash transaction volumes will reach 1.3 trillion by 2023 globally. As consumers and businesses adopt new digital payment schemes, an FT report suggests this growth will accelerate to 2.3 trillion by 2027 growing at a rate of 15% annually. At a regional level, digital payments will grow by 19.8% across Asia Pacific, 10.7% in Europe, and 6.5% in North America by 2027.
- These manual or even legacy systems are slow to run, demand high levels of manual intervention, and are unable to keep up with the performance and scalability requirements of today’s screening needs.
2. Regulatory compliance challenges:
- Increasing transactional volumes are increasing instant payments and the need to check transactional data in real-time.
- Opaque algorithms based on thresholds and legacy technology are not providing the explainability regulators need to operate effectively.
- Inflexible rules and workflows make it difficult to reconfigure the system to keep pace with frequently changing sanction regimes.
3. Complexity of name screening
There are lots of challenges that the screening system must be sophisticated enough to deal with:
- Multiple types of error, such as phonetic similarity e.g. Luca vs Luka
- Missing words and names
- Multiple last names
- Partial name matches
- Name variations (e.g. Nick, Nicholas)
- Spelling errors
To add to these complexities, many criminals intentionally set out to manipulate screening systems. The screening system therefore needs to be sophisticated enough to limit the frequency of false positives under the pressure of facilitating instant payments, without discounting any true matches. This is why financial institutions need machine learning and artificial intelligence (AI).
The optimal screening solution for instant payments
Contextual name matching
NextGen Client Screening leverages sophisticated name matching engines at the core that can be tuned even more accurately to cover all the cultural contexts in which a bank transacts, reducing risk in global banking. This includes capabilities to match name variations from phonetic similarity, transliteration, nicknames, misspellings, multiple scrips, semantically similar and truncated components, initials, and related inconsistencies across data fields to ensure accurate identification. This can result in up to a 90% reduction in false positives.
It’s important to apply multiple similarity algorithms and models to get an accurate match, including:
- Phonetic similarity – For example, Gemma Payne vs Gemma Pain.
- Cultural similarity – You need to understand what could or could not be more important, such as choosing to be known by second name rather than a first name in western countries.
- Words – Are any words missing?
- Order – How are you looking at the matches of the whole name, the individual parts of that string and the order of those parts?
By feeding in risk policies and information from historical reviews into screening AI, you can achieve a good determination of whether to discount or review with an easy to understand explanation. For example:
- 'John Taylor' vs 'Mark John Taylor'
The AI system would discount this match because of the dissimilar first name component.
- 'Bak Real Estate' vs 'Real Estate Bank'
The AI system would review this match. Bak could be a spelling error but there may also be an intentional movement of words to bypass the system.
- 'John Snow' vs 'Snow'
While most legacy systems would flag this match, the AI system would discount because data records show John Snow is a person and Snow is a vessel. The system has incorrectly matched different types of data.
- 'Paul Mirano' vs 'Iran'
The AI system would discount this match because the context of ‘iran’ in a person’s surname is not related to the sanctioned country. Most legacy systems would however flag this for review.
Multi configuration screening
NextGen solutions must support multiple configurations of screening strategies to enable an optimal risk-based approach to meeting the evolving regulatory requirements of all jurisdictions in which the bank operates.
Real-time screening
Legacy processes and systems create an unacceptable lag in onboarding between accepting a new customer and identifying their true risk profile. NextGen solutions will support screening of customers in real-time against external data and internal lists which are updated more frequently than ever.
Cloud native
Banks have lagged other industries when it comes to leveraging the cloud for mission-critical applications. NextGen solutions should be cloud native and offer compliance certifications and standards, such as ISO 27001 and SOC 2.
Low-code
NextGen solutions are low-code, meaning the financial crime compliance (FCC) team from the front to the back office can configure the dashboards and views, reports, rules and workflows they need.
Integrated sandbox
An integrated sandbox allows users to test rule sets and configurations using real data, to ensure optimum results before deploying live, and avoiding any unanticipated customer impact. An integrated sandbox should also be able to leverage synthetic data, to take advantage of public-private partnerships, including regulatory sandboxes, to ensure that testing is done on data representative of the entire market not just the current customer base. It should also enable ‘what if’ or scenario testing that determines potential future threats and risks.
Explainable AI
Global regulators are now issuing guidance around the adoption of AI for financial crime compliance, with one thing in common: explainability. Any AI leveraged in the FCC process must be used to inform and support a decision made by a human, not autonomously action the outcomes of its calculations.
Final thoughts
In the past screening challenges were seen as a compliance issue. Now with the increasing demand for instant payments, they are becoming customer problems that are having a negative impact on customer experience.
Artificial intelligence holds huge potential for overcoming these challenges by adding another layer of review. It provides additional confidence and focuses human resources onto the hits deemed to present the greatest risk. By modernizing screening solutions, financial institutions can greatly reduce the risk of non-compliance.
Photo by Ash Edmonds on Unsplash
