An effective screening system relies on both exact and inexact name matching for accurate identification as fraudsters often transpose names and other data trying to conceal their true identity.

Fuzzy matching is a technology that identifies spelling variations of the names and other search terms in case a character was omitted, inserted, or replaced, either occasionally or on purpose.

Fuzzy logic capabilities

Apart from catching spelling errors, fuzzy logic is extremely helpful for screening names that have been transliterated from non-Latin scripts. This lets you avoid missing true positives due to geographic, cultural, or other differences, such as:

• Transcription variations, e.g. Husain, Hussein.
• Homophones (equivalent pronunciation), e.g. Jaqueline, Jacklyn.
• Phonetic matching, e.g. Irbah, Ibra.
• Hypocorisms (shortenings), e.g. James / Jimmy / Jim.
• Common abbreviations (for entities), for example, ‘Ltd’ instead of ‘Limited’.

📘

Note

Fuzziness is not performed on non-Latin characters.

How do we cope with false positives

A false positive is a screening result that the system considers a match, but in reality, it is not. To cut false positives to a minimum, we capped the maximum edit distance change at one character.

Manage fuzzy matching results

The fuzzy matching results are located in the Watchlists section of the applicant profile and are marked as Fuzzy match. The Name column lists all potential applicant name matches found in various watchlists and adverse media.

If you disagree with the fuzzy matching results, you can change the status of the match in the corresponding column to False positive.