Identity Analytics Icon

AML, KYC, PEP

Image collage of shapes with different denominations of money masked within a hexagon.
Person counting money with nodes in background

Anti-Money Laundering (AML)

Accurately screening names against sanctions and watch lists for AML is a critical priority for organizations in the banking, financial, and money transfer industries as the consequences of missing a match can be severe.

The challenge lies in the wide variability of names due to misspellings, nicknames, missing elements, abbreviations, initials, or changes in word order. Furthermore, screening names from various cultures and ethnicities poses additional complexity, including transliteration variants, tokenization differences, ethnicity-specific variations, and the use of different writing systems.

Machine learning-based NetOwl NameMatcher and NetOwl EntityMatcher bring AI to AML screening, maximizing accuracy while minimizing false positives. Trained on large-scale, real-world, multi-ethnicity name-variant data, NetOwl consistently outperforms traditional name matching approaches.

Multilingual Know Your Customer (KYC) Screening

Financial institutions and other regulated businesses are required to verify the identity of their customers in what is known as the Know Your Customer (KYC) process, which is part of anti-money laundering (AML) and counter terrorism financing (CTF) regulations. KYC applies not only during onboarding of new customers but also in periodic reviews of existing customers.

As companies go global, the records they must match also go global and multilingual. Names may be written in not only English but also other alphabets and writing systems such as Chinese, Arabic, or Cyrillic. Effective screening therefore requires the ability to match names both within the same writing system and across different writing systems – for example, between English and Arabic. 

With built-in support for multilingual and cross-lingual name matching, NetOwl ensures exceptional high accuracy and speed.

Illustration of a global network with nodes in background
Chess piece taking queen with nodes in background

Building a More Comprehensive Politically Exposed People (PEP) List

A Politically Exposed Person (PEP) list includes prominent public figures – as well as their immediate family members and close business associates – who may present a heightened risk of involvement in corruption, bribery, or money laundering. As part of AML and KYC processes, PEP screening helps organizations mitigate these risks and protect their reputations. Currently there is no official PEP list. Instead, multiple organizations provide such lists with varying degrees of coverage.

NetOwl Extractor can drastically improve the quality and coverage of a PEP list through its advanced text analytics capabilities. Its entity, relationship, and event extraction enables continual update of the PEP list by analyzing vast amounts of various open-source data – including news, web pages, and social media in English and other languages – in real time and identifying concepts such as:

  • Names of individuals and descriptive phrases that indicate a PEP (e.g., “Jaime Freire, the newly appointed Minister of the Interior”)
  • Relationships like kinship (e.g., “the minister’s wife, Lorena Asencio”) and professional or personal associates (e.g., “his former business partner at XYZ Corp.”)
  • Events related to official roles or interactions, such as appointments, hires, and meetings that can surface additional public figures and associates within the PEP’s circle.
Light gray diagonal shape spanning the full width of the canvas.

Featured Blog Posts

Name Matching is Crucial for Transaction Screening as Part of AML

How Name Matching is Crucial for Transaction Screening as Part of AML

Transaction Screening for AML compliance requires screening of both the sender and the beneficiary of a transaction against various databases…

View Post

Cross-language name matching is crucial for customer verification and vetting

How Cross-Language Name Matching is Crucial for Customer Verification and Vetting

In a global economy, financial institutions face the challenge of verifying and vetting their customers’ identity data across different writing…

View Post

Entity Extraction plus Name Matching are critical for up-to-date KYC data

How the Combination of Entity Extraction and Name Matching is Critical for Up-To-Date KYC Data

KYC Data Providers face the challenge of how to ensure their data is comprehensive and up-to-date in an ever-changing world…

View Post