First AML leverages third party data providers in order for our analysts to perform various verification checks on individuals. We have enhanced the way in which the results of these verification checks are presented in the Platform.
The report consists of a high level summary of the verification checks and then a more detailed summary of the verification check results.
TABLE OF CONTENTS
- Verification Results
- Verification History
- ID Document and Biometrics Check Results
- 1. ID Document Report
- 2. Biometrics (Facial Recognition) Report
The results of the verification checks include;
- Date of Birth
- ID document
Each of these checks will result in either a PASS or a FAIL, based on whether the information provided matches the databases checked.
Note: Australia and United Kingdom EIV legislation differs slightly to New Zealand. Two different sources must be checked in order to pass an individuals name, date of birth and address, however the ID does not have to pass.
Below is an example of this, you will note the Red X's next to some of the sources checked, however the overall outcome of the EIV is still a PASS.
Each of these checks will result in either a PASS or FAIL.
- Adverse Media
PEP - A politically exposed person is an individual who has been entrusted with a prominent public function and potentially presents a higher financial risk due to the influence they may hold
Sanctions - Financial penalties that have been applied by a country or countries against an individual or entity.
Adverse Media - Any negative information on an individual or entity discovered across various sources, i.e. reputable news or other publications linking the individual or entity to involvement in corruption, money-laundering, terrorism/threat financing and other unlawful activities.
Each of these checks will result in either a MATCH (where the individual has triggered 1 or many hits) or NO MATCH (where the individual’s check has returned 0 results).
For each section of the report that is presented, it will include details of the name, date of birth, address and ID document (if applicable) that was provided to First AML. There will be a related status, and the various data sources that were checked in the process. In some cases, our analyst team may need to reach out for further information in order to successfully complete the verification.
The PEP, Sanctions and Adverse media section indicates where there has been a match. Clicking on this will take you to a more detailed report that allows you to further investigate the matches.
At the bottom of the report there are two sections; History, and the Legacy verifications. The History table will list out all verification reports (new) that have been generated for this individual. The Legacy verifications table will include all those legacy verification reports (prior to the new verifications report) generated for an individual.
ID Document and Biometrics Check Results
The ID scan and biometrics result is made up of 2 reports. Each report returns a result which in turn contributes to the overall profile status.
- ID Document Report
- Biometrics (Facial Recognition) Report
Interpreting the Results
1. ID Document Report
The Document report employs a variety of techniques designed to identify fraudulent documents. It checks the internal and external consistency of the identity document provided by the applicant to identify potential discrepancies. The overall result may show clear, caution, suspected, or rejected as outlined below.
Document Report Result Breakdown
Asserts whether the document was of sufficient quality to verify.
Asserts whether the image was a colour one.
Conclusive Document Quality
A result of clear for this sub-breakdown will assert if the document was of enough quality to be able to perform a fraud inspection.
Asserts whether the submitted document is supported.
Asserts whether the quality of the image was sufficient for processing.
Asserts whether visual (non-textual) elements are correct given the document type.
Asserts whether algorithmically validatable elements are correct. If 'Document Expiration' shows a flag, this means that the document has expired. If 'Expiry Date' is flagged, this means that the expiration date has the incorrect format.
Asserts whether data represented in multiple places on the document is consistent. For example, between MRZ lines and OCR extracted text on passports.
Asserts whether the image of the document has been found in our internal database of compromised documents.
Asserts whether the document has been identified as lost, stolen, or otherwise compromised.
Biometrics (Facial Recognition) Report
Compares the photo or video provided by the applicant to the face on the document provided. It aims to prove identity document ownership so that only the owner of the identity document can use it to verify their identity and access services. The facial recognition report has an overall result, which is either a clear or a consider. When they receive a consider, the report breakdowns will indicate any issues found. Depending on the reason, and your risk appetite you may decide to reject the user, or manually review and override the result.
Facial Recognition Report Result Breakdown
Asserts whether the quality and integrity of the uploaded files were sufficient to perform a face comparison.
Asserts a single face of good enough quality has been found in both the document image and the live photo. This will return a consider if no face is found on the front of the document, or no face is found on the selfie or video, or too many faces were found on either.
Asserts whether the selfie or video is trustworthy. This will return a consider when a selfie or video is found to be digitally tampered with, from a fake webcam, emulator, or from other dubious sources. It indicates deliberate attempts at defrauding the system.
Asserts whether the face in the document matches the face in the live photo.
This will flag as consider when the person doesn't match the face on the identity document. A similarity score will also be returned. The closer to zero that score is, the less likely the two faces belong to the same person.
Asserts whether the person in the selfie or video is real.
This will return a consider when the selfie or video contains a face that is not real, also known as a spoof. For example, a face on a piece of paper, a face on an identity document, a face on a digital screen, a screenshot, etc. A spoofing score will also be returned. The closer to zero that score is, the less likely the face is real.
The confidence score is surfaced as a percentage. Confidence in the result on a scale of 0 (no match) to 100 (strong/identical match). Whole integers only.
< 40 if the results are highly ambiguous and probably not a match. Default to 0 rather than 40 if at all in doubt.
41-70 if the results are partial matches. Use your judgement and common sense to come up with a useful number
70-90 for results where there might be a small amount of uncertainty, but we’re pretty confident they’re for the right person/document.
90+ for high levels of confidence.
NOTE: This score is not perfectly reliable and should not be used out of context.