Ripjar

How does entity-based screening differ from traditional name matching?

Traditional name matching compares a customer name against risk lists and returns individual hits. Entity-based screening resolves each person or organisation into a dynamic profile that accumulates context from sanctions, PEPs, other watchlists and adverse media over time. Prior decisions carry forward, so analysts start each review with context rather than a blank screen.

What data sources does Ripjar Screening integrate with?

Ripjar is data-agnostic by design. It integrates with sanctions lists (OFAC, EU, UK, AUSTRAC and others), PEP databases, a range of adverse media sources and your own internal datasets. There is no lock-in to a single data provider.

How long does implementation typically take?

Implementation timelines vary depending on the complexity of the deployment, data sources and integration requirements. Ripjar works with each customer to define a phased deployment plan. Cloud-based deployments are typically faster than on-premises installations.

Can Ripjar screen in multiple languages and scripts?

Yes. Ripjar’s proprietary name matching is built on over one million name variants across 20+ scripts and 400+ languages for name matching. It resolves transliterations, aliases, diminutives and organisational name parts with 94% improvement over traditional fuzzy text matching.

How does Ripjar handle false positives?

A false positive is a screening alert that identifies a potential match to a risk list but, upon investigation, is determined not to refer to the same person or organisation. Ripjar reduces false positives through three mechanisms: entity resolution (separating lookalikes early), dynamic profiles (retaining prior decisions so resolved matches don’t re-enter the queue) and Screening Assistant (specialised, explainable AI triage that auto-closes low-risk items with a full audit trail). In live deployments, customers have seen false positive reductions of up to 91%.

What does a false positive cost in AML screening?

Industry estimates put the cost of reviewing a single false positive alert at $30–$70, with enterprise screening programmes generating thousands of alerts per day. At false positive rates of up to 95%, the majority of analyst time and budget is consumed by irrelevant matches.[8] Beyond the direct cost, unresolved false positive volumes create backlog pressure, increase regulatory scrutiny and divert resources from identifying genuine risk.