The NetReveal AML Optimisation solution is a self-service module that gives financial institutions the ability to define, monitor, and deploy detection profiles for improved anti-money laundering model accuracy, effectiveness and lower false positive alerts without reducing true positives.
Financial institutions are overwhelmed with the increasing volume of alerts generated by mandatory transaction monitoring systems and are unable to maximise their investigative resources. Industry estimates suggest at least 95% of the alerts are false positives. Identifying and reporting on truly suspicious activity is getting harder and putting greater burden on investigation teams.
Financial institutions using outdated detection models that remain unchanged from their original creation and implementation may be leaving many suspicious transactions undetected. Constantly evolving threats require continuous scenario improvement.
Regulatory authorities are increasingly leaning on institutions to not only justify the rationale behind AML model changes, but also to validate the efficacy of existing models and the assumptions on which those models were built as part of a wider model risk governance program.
Optimise AML Detection Scenarios
NetReveal AML Optimisation is a packaged, user-friendly solution to improve the efficacy of an AML transaction monitoring and detection program.
It is a sophisticated analytical solution that can work in conjunction with the NetReveal AML Transaction Monitoring solution. In-house analysts can visualise and compare scenario performance, identify underperforming parameters, test changes, and promote them to production – without the need for lengthy and expensive consulting engagements. Machine learning algorithms can also be scheduled to review detection results of rule-based monitoring systems and propose the optimal parameters that make up those rules.
NetReveal AML Optimisation is a self-service solution that provides:
- Profile store manager for AML Optimisation big data – compliance analysts can define, monitor, and deploy profiles directly within the solution to improve and speed up decisions. Easily simulate true positive and false positive rate changes within the production scenarios
- Machine learning algorithms – can be scheduled to review detection results of rule-based monitoring systems and propose the optimal parameters that make up those rules. The approach significantly reduces false positives, improves efficiency, and lowers operation costs
- Model management and audit logging – optimises model governance by giving analysts the ability to demonstrate to auditors and management their rationale and justification behind decisions made for scenario model changes
- User-friendly interface – a packaged, easy to use solution, that’s designed specifically for analysts, not data scientists or engineers. Parameters can be tuned, analysed and tested in a visual way for quick interpretation and remediation
BAE Systems named a “Category Leader” in Chartis Financial Crime Risk Management Systems: AML and Watch List Monitoring 2019 Vendor Landscape report.
Chartis, Financial Crime Risk Management Systems: AML and Watchlist Monitoring 2019.