Compliance & Risk

Weak signal, ranked priority. Noisy alert, explained.

For AML, KYC, sanctions, regulatory and enterprise risk teams.

Rule-based monitoring produces thousands of alerts, 95% of them false positives. The real risk hides in the weak signals: a small change in ownership, an adverse-media hit in a foreign language, an unusual counterparty chain. Compass enriches each alert with full network context and reasons like an analyst — with every decision explained and logged.

The problem

Analysts spend 70% of their time clearing noise. Real risk gets buried, remediation windows close, and every regulator ask becomes a scramble across ten systems to reconstruct the reasoning.

Data we integrate
  • 01Core banking & transaction monitoring (Actimize, SAS, Oracle FCCM)
  • 02KYC / CDD platforms, onboarding & customer master
  • 03Sanctions & PEP lists (EU, UN, OFAC, HMT, national)
  • 04Company registries & beneficial ownership data
  • 05Adverse media (multilingual), court filings, gazettes, regulatory feeds
How we contextualize
  • Merges alerts with the full counterparty network — one hop, two hops, N hops.
  • Explainable scoring: every risk score comes with the evidence and the rule it fired.
  • Multilingual adverse-media matching with entity disambiguation.
  • Full audit trail — who saw what, when, and why the decision was taken.
What you get out

Reports, decks, Excel, dashboards and alerts — ready to ship.

Brief (PDF)

Alert triage rationale

Per-alert PDF with the enriched network, evidence sources, prior decisions and the analyst-ready rationale.

Excel

Regulator response pack

Structured Excel with cases, decisions, dispositions, timestamps and evidence links — ready for the request.

Dashboard

Alert operations dashboard

SLA, false-positive rate by rule, backlog aging, analyst load, escalation funnel.

Audit log

Immutable decision log

Every action, override and reason captured — inspectable end-to-end by second-line and audit.

Alert

Priority-ranked queues

Alerts routed to the right analyst, ranked by real risk — not by chronological order.

A concrete case

AML backlog cut 62%. Real risk found faster.

A mid-tier bank was drowning in 8,000 monthly AML alerts. Compass enriched each alert with counterparty networks, ownership graphs and multilingual adverse media, and re-ranked by real risk. The backlog dropped 62%, false positives fell by half, and the model surfaced two previously overlooked cases involving nominee owners two hops from a sanctioned entity — with a full evidence chain the second-line signed off in an afternoon.

Trust by design

Evidence, explainability, audit — built into every output.

Source-level evidence

Every signal, score and recommendation links back to the underlying record — the email, the filing, the transaction, the document — with the source visible at a click.

Explainable recommendations

No black-box outputs. Each priority states why it was promoted, which signals contributed, which were declassed, and which model version produced it.

Audit trail by default

Signals, model versions, reviewers and actions are logged and reconstructable later — ready for internal control, regulators and your own governance.

Human-in-the-loop

Compass recommends. Authorized people decide. Every consequential action requires a named reviewer who can confirm, override or annotate the reasoning.

See Compass on your data.

We bring a demo on your domain: which relationships emerge, which signals fire, which outputs we could deliver today.