Achieving AML compliance
with Labyrinth Screening
Ripjar’s Labyrinth Screening product enables you to understand customer and counterparty AML risk by screening new and potential customers, vendors and supply chain against watchlists, PEP lists, sanctions lists and news media.
Advanced machine learning
Ripjar AI Risk Profiles
Staying on top of your sanctions screening is particularly important in a fast-changing risk environment, so Labyrinth Screening makes it easy to ensure you’re always aware of the latest sanctions affecting your customers.
Politically Exposed Persons
Anti-money laundering regulations around the world require screening for politically exposed persons (PEPs) because of the increased criminal risk that they present.
As well as sanctions lists, it is essential to screen against a wide range of watchlists to identify any further people or organisations which may be associated with additional financial risk.
Adverse media screening is increasingly becoming a critical component of AML processes and having an effective system in place is vital. For example, the EU's 6th Anti-Money Laundering Directive (6AMLD) mandates systematic checking against adverse media - specifically to detect the 22 predicate offences which often precede money laundering.
Market-leading adverse media screening
Learn more about our Adverse Media Screening solution here.
Trusted By Global Businesses
Ripjar has a pedigree in supporting European financial institutions, as well as those that run operations across the globe. This made them the perfect fit to support the requirements of VP Bank.
Together, we are taking a time-consuming, manual process and applying state-of-the-art automation with more insights into data to not only improve accuracy, but also give management complete audit capabilities and accountability over the entire screening process.
The AI technology embedded in the system could also reduce data-reporting errors by over 80%, when compared to third-party legacy systems.
We demonstrated a 13% improvement in recall and simultaneously a 91% reduction in False Positives as measured by our model validation team on an unseen dataset.