SAS is the first financial crimes solution vendor to offer rapid testing and deployment of anti-money laundering (AML) scenarios in big data architectures. SAS® Transaction Monitoring Optimization includes advanced visualization capabilities with an industry-vetted methodology for segmentation, validation, tuning and simulation of AML models. The solution helps banks reduce costs and increase program effectiveness, thanks to the ability to visualize patterns rapidly.
Using SAS in-memory architecture, business analysts can now create, challenge and simulate AML models rapidly against large data volumes. With embedded industry best practices for model risk management, SAS Transaction Monitoring Optimization helps institutions support themselves instead of relying on third parties.
“Model risk management is an increasing point of focus for AML regulators – they want to know that financial institutions understand how their AML analytics work, and that any tuning is not hampering detection efforts,” said Julie Conroy, Research Director at Aite Group. “They want to see evidence that systems work via demonstration, explanation and documentation. It’s critical that solutions provide the flexibility to quickly modify scenarios and can visually show how and why changes were made. The new enhancements from SAS are a testament to their leadership in streamlining the process for improved regulatory reporting.”
SAS Transaction Monitoring Optimization includes three visualization capabilities:
- SAS Visual Analytics helps identify patterns of emerging risks quickly and clearly. Business analysts can recognize macro patterns that may represent new or potential risks. Once risks have been identified that require coverage, further analysis can be conducted to formulate a strategy for monitoring. Visual dashboards can communicate operational metrics and trends to stakeholders through tablets or mobile devices.
- SAS Visual Statistics empowers data scientists to build models visually. Quantitative end-users can visually build statistical models instantly, seeing the correlation between variables and potential suspicious activity. Statistical analysis is instrumental in supporting policies for coverage and prioritizing risks. Data scientists can apply unsupervised methods like clustering to create customer segments for peer-based anomaly detection.
- SAS Visual Scenario Designer transforms the process for scenario and strategy management. In-memory architectures enable users to test scenarios and strategies and simulate them against vastly larger quantities of data, allowing multiple simulations in seconds versus hours. Business analysts can drag and drop scenario attributes into rules to analyze their impact on productive investigations. Testing scenario modifications against big data volumes means more accurate operational impact analysis and effective application of resources to emerging financial crimes risks.