Napier’s Transaction Monitoring is a powerful solution that provides a systematic, intelligent review of an organisation’s transactions. It is simple to deploy and is designed to be used by non-technical business users.

Built on big data architecture, it can handle 100’s of millions of transactions with ease and enables businesses to rapidly strengthen their AML and CTF defences.

Define and build rules
Define and build rules easily with the intuitive interface that requires no coding to minimize false positives and detect anomalous transactions.

Our system provides a full audit trail on all user- and system- generated actions and automates processes throughout the workflow.

Simulate, test and deploy
Test and iterate new rules easily in Napier’s Sandbox.

The clear interface and drop-down menus make it simple to build rules and scenarios on real data, then test before going live.

As intelligence about suspicious behaviours is gathered, scenarios can be repeatedly tested to create even more effective rules. This flexibility means users can respond nimbly to changing compliance requirements and to changing criminal behaviours.

Enhance your analysis
Use machine learning to enhance transaction monitoring outcomes.

Our system produces two scores: one from rule-based scenarios; and the other from advanced machine learning algorithms. Compare these scores to understand and prioritise daily workload.

Using a combination of transactions, watchlists and historical customer behaviour our algorithms complement traditional rules-based reviews of customer activity and identify patterns that are difficult to spot amongst high volumes of data.

Manage cases and workflow
Teams can manage cases through a single, self-auditing platform that defines and unifies every step of an investigation.

View only the data that is relevant to a defined workflow with our highly configurable dashboard.   With access to a palette of over 80 widgets, users can control and configure what they see to ensure it is relevant and specific to their task.