AML AI has MANDATORY fields which are essential for the detection of money laundering, such as transaction value and time. The product also has RECOMMENDED fields which are used to improve risk coverage, for fairness analysis, and to help manage data lineage.
To optimize coverage, you should provide RECOMMENDED fields because some of them enable additional features that are critical risk indicators for some typologies.
Data fields categorized as RECOMMENDED can improve risk typology coverage in two ways:
- By supporting typologies that don't have any supporting features calculated from the MANDATORY data fields (for example, money laundering through high-risk jurisdictions)
- By strengthening the coverage for an already supported typology with new features that yield additional results (for example, money muling)
The following table summarizes the purpose of all RECOMMENDED fields in the AML AI schema.
| Field | Tables | Performance impact? | Typology coverage impact? | Other uses |
|---|---|---|---|---|
nationalities | Party | Yes | Yes, multiple | N/A |
residencies |
Party | Yes | ||
birth_date | Party | Depends on engine version | Yes, multiple | Field can be used for your own fairness analysis. |
establishment_date |
Party | Depends on engine version | Yes, multiple | No |
gender
| Party | Depends on engine version | Yes, multiple | Field can be used for your own fairness analysis. |
is_entity_deleted | No | No | Field can be necessary to correctly model how entities change over time, depending on how you manage your data internally (see Understanding how data changes over time). | |
source_system | No | No | Field helps you to manage dataset quality. |