By PAUL O’DONOGHUE, Senior Correspondent
RIPJAR has introduced new AI capabilities to its customer-screening platform to improve adverse media screening and combat financial crime risks.
The London-based company said that the updates to ULTRA, its “real intelligence engine”, would help compliance teams identify and manage risk with greater speed and clarity.
Ripjar said ULTRA is used by more than 400 organisations globally, including 25% of Global Systemically Important Banks and more than 35 companies in the Fortune 500.
The platform uses proprietary graph algorithms, transformer models and custom AI to process more than 10 billion historic articles and more than 5 million new articles a day across more than 150 languages, according to Ripjar.
The company said ULTRA is built on “national security grade technology” and combines data on politically exposed persons, sanctions, watchlists and adverse media into a single profile for each entity.
Ripjar said this creates a “complete 3D view of risk” and allows risk to be assigned to the correct entity with 98.7% accuracy. The company said this can reduce the number of alerts reaching an analyst by 99%.
Ripjar screening tools
The latest updates include changes to Screening Assistant, Ripjar’s agentic AI tool for alert triage. The company said the technology is designed to “further reduce routine alert handling, improve decision-making and increase risk coverage”.
ULTRA’s entity-matching capabilities have also been upgraded. Ripjar said the changes allow customers to better distinguish between parent organisations, subsidiaries and similarly named entities.
The update also improves Screening Assistant’s handling of “complex naming conventions, including Arabic names”, according to the company.
Ripjar has also upgraded ULTRA’s adverse media risk classifiers. These analyse news articles to determine whether they relate to a specific risk and identify the person involved.
The company said the latest upgrades move ULTRA to a “new generation of machine learning”, improving existing classification and entity-resolution capabilities.
Conrad Nicholas, chief product officer at Ripjar, said ULTRA uses multiple layers of AI to remove duplicate information, resolve references across billions of articles and attribute risks to the correct person.
“What sets ULTRA apart is orchestrating these models at scale with explainability built in,” Nicholas said.
Matt Mills, CEO at Ripjar, said: “AI is vital but compliance teams need to understand and trust its decision making.”
Ripjar said every alert, decision and summary produced by ULTRA is “backed by evidence, traceable to its source” and held in an auditable system of record designed for regulatory scrutiny.
We hope you enjoyed reading this article
If you would like unlimited access to AML Intelligence premium articles, newsletter delivered twice a week, access to our Global Bank Fines and Penalties database, free access to Boardroom Series events and much more, select one of our subscription options and become a subscriber!
