That's not my name: challenges in KYC name matching

January 25, 2022

Culture, geopolitics, and media reporting all create challenges for name matching, even when software performs the matches. In this, the first of our anthrolinguistic insights series, we show how GRID data and Review screening work against the background of these broader trends.  

A subtle theme underpins know your customer (KYC) risk screening: names. A personal name is an individual’s most unique identifier and is often mentioned in related adverse media. Moody’s Analytics KYC solutions consider several identifying components, including an individual’s location and date of birth, but the driving force behind generating accurate alerts is matching based on a name.  

This might sound simple, but it’s not. Names can be quite complicated. Name matching is especially difficult in a global dataset of names captured by sources including government watchlists and adverse media from more than 240 countries — in more than 70 languages and numerous scripts. The complications grow when the names include those of risk-relevant persons and organizations, some of whom may want to avoid detection.  

To manage this process, Moody’s Analytics KYC has established a team of cross-functional screening specialists. This team combines qualitative anthrolinguistic expertise with tailored quantitative data science algorithms to overcome name-matching challenges and deliver sophisticated results.

Not just a numbers game

Software is simple, but people are not. Creating software about people for people is no walk in the park. Accommodating the complexities of our existence — like our identities— requires several considerations.

Naming conventions

A plethora of naming conventions exist around the world, related to the ordering of personal, familial, and cultural names. Surnames or family names may come at the beginning or end of a full name and may differ, depending on the person’s gender. For example, in Russian-speaking cultures women’s surnames commonly end in ‘a’, but this ending would be omitted from their brothers’ surnames.

Arabic naming conventions present a particular challenge for name matching, because name order generally does not map directly to that of other cultures — the inclusion or exclusion of honorifics or other name parts varies widely. The diaspora of Arabic names corresponds with the inconsistencies in name recording.

Name order can also be important in distinguishing names in cultures with similar naming conventions. For instance,  Lusophone names tend to have the maternal surname followed by the paternal, whereas the opposite is usual for Hispanic names.  

Naming traditions

Some cultures maintain significant or symbolic names for generations, leading to names that are common to many people. For example, middle names in Vietnamese cultures tend to correspond with birth order, offering less identifying information than an additional name component generally would. Such customs raise questions around how best to capitalize on distinct elements of names in software design to avoid overwhelming screening results with false positives.  

Moody’s Analytics has three main avenues for identity disambiguation among common names:

  • GRID profiles maintain high-quality standards on identifying data, including date of birth, addresses, and aliases, particularly among premium content profiles enhanced with entity-based research.
  • Customizable filters for alias, address and date of birth analyze and rule out matches with conflicting identity information.
  • Review provides additional post-match research on GRID content profiles to reduce alerts to only high-confidence matches.

(Un)popular names 

Names are subject to popular trends resulting from famous figures, waves of migration or baby booms. Just as easily, names can significantly decrease in popularity. The notorious ‘bad guys’ of GRID today might deter the popularity of their names in the future. It only takes one bad reputation to cause trouble for their namesakes, which may be why some jurisdictions outlaw some names.  

Name recording

Recording a name from one medium to another can easily introduce errors — especially when the name is transliterated. Who audits how an entity name went from point A to point B? Audio-to-text transcription adds many problems but relying on a signature to spell a name can also be problematic.

Luckily, with modern word processing, we don’t often have to rely on handwriting to spell a name. However, the adoption of digital records, literacy rates, and access to computers remain uneven between and even within countries. Name recording may rely on optical character recognition, which gives near-accurate, yet sometimes imperfect interpretations of written documents and letters. Even where digitization is widespread, software can introduce errors — for example, automatically ‘correcting’ ‘Kara’ to ‘Lara’ or ‘Mark’ to ‘Park’.

Identifying a misspelling across languages and scripts makes disambiguation less intuitive than it would appear to be. The range of keyboard templates adds to such unpredictability. Languages that use the same alphabet may use unique keyboard layouts, like French and English, whereas logographic scripts might succumb to the ‘Wubi Effect’, where several competing keyboard configurations are in common use among a community with a single common language.  

Our Review software incorporates targeted intelligence on appropriate name variants to accommodate transliterations, as well as misspelling frequency data to interpret possible typographic errors and prioritize relevant alerts.  

Geopolitical impacts  

Languages, scripts, writing standards, and cultural pressures differ between regions and change over time. Political power plays a surprising role in how names are written, recorded, and transliterated. For example, imposing the Russian language and Cyrillic alphabet in the Soviet republics, as a tool for social cohesion.

In other cases, it’s about cultural revitalization. The near-extinct Gaelic language was revived after Ireland became independent in 1922. As recently as 2005, a law came into force that mandates Gaelic versions of place names in parts of the country’s west on road signs and official maps.  

Issues of identity

What makes name matching even more complicated is when the names of one person don’t match — and by all linguistic means should not match. Some people may not want to be identified, but name changes also have other justifications. Legal name changes are more common in some places than others and are often subject to regulation. In 2005, South Korea’s supreme court allowed name changes under certain conditions, such as if the name resembles an offensive word or is the name of a famous criminal. Under this law, a person cannot change their name if they have a criminal record or history of bankruptcy. Elsewhere, an individual might go by a different name due to cultural pressure or a desire to assimilate, or perhaps to make it easier for others to pronounce their name.  

GRID profiles capture all available aliases as recorded in adverse media coverage to ensure identification of risk entities. Further research is included with our high-risk premium content sets, such as politically exposed persons (PEPs) + family or close associates, Iran Connect and Sanctions Connect. Review screening also includes critical watchlist logic and optional OFAC-search style algorithms to detect high-risk sanctioned entities.

Overcoming the challenges

Moody’s Analytics KYC name matching is designed to promote operational resilience for our clients; our KYC solutions help you make more accurate, better decisions faster, and reduce barriers to working with people worldwide.

Our experts analyze GRID data data, identifying reporting trends in name variants across regions - as well as changes over time. And those insights guide GRID software development.

GRID name-matching teams constantly innovate and develop software and expertise to overcome complex, cross-cultural realities. We rely on software intelligence and development, robust governance processes and support, and anthrolinguistic expertise and insights for a customizable and consultative approach to risk-screening best practices.  

Subscribers to Moody’s Analytics View can visualize name trends in their own portfolios, along with alert-decisioning data to adjust their filterable configurations.

Moody’s Analytics AI Review adds machine learning that reduces alerts based on a combination of a global GRID model and local client model.    

Contact us to learn more about our name matching capabilities or for a GRID and Review demo.

Download now
Listen on: