Modernize your existing AML solution by operationalizing AI and machine learning in the cloud. Lower compliance costs by reducing false positives, automating investigations and improving detection.
Boost the productivity of your AML analytical teams.
Empower data scientists, business analysts and other analytics professionals with highly accurate results from a single, collaborative environment that supports the entire machine learning pipeline. A variety of users can access and prepare data, perform exploratory analysis, build and compare multiple AML machine learning models, autotune hyperparameters and execute one-click model deployment.
Dramatically reduce false positives and eliminate unplanned model tuning efforts with ongoing optimization.
Always keep your AML models performing at their highest levels with performance benchmarking reports and alerts generated for easy tracking to indicate model decay. Ongoing monitoring identifies when it’s necessary to refine or retire a model. And model retraining integrates with the model pipeline processing environment for increased efficiency.
Explore multiple approaches quickly to find the optimal solution.
Easily build and train AML machine learning models with a user-friendly drag-and-drop interface. Users can explore and compare multiple models quickly. Find the optimal parameter settings fast for diverse machine learning algorithms – including decision trees, random forests, gradient boosting, neural networks, support vector machines and factorization machines – simply by selecting the option users want. Users can also combine unstructured and structured data in integrated machine learning programs for more valuable insights from new data types.
Ensure transparency with explainable AI and machine learning
Standard interpretability reports are available in all modeling nodes, including LIME, ICE, Kernel SHAP, PD heatmaps, etc., with explanations in simple language from embedded natural language generation capabilities.
Improve operational efficiency and gain a single view of the customer.
Examine alerts post-generation using predictive models to determine whether they are false positives. You can wrap this model around an existing AML platform to identify poor-quality alerts so investigators can spend more time on higher-value cases and significantly increase their investigation efficiency. Apply machine learning to account for inconsistencies, errors, abbreviations and incomplete records for resolving entities and creating a holistic view of risk through a single, global customer ID.
KEY FEATURES
Connect your existing transaction monitoring system to an advanced analytics environment in the cloud. Enhance your anti-money laundering (AML) program's overall efficiency and effectiveness with artificial intelligence (AI) and machine learning.
Easy data exploration & visualization
Lets you easily import your own data, build and run transformations, and augment and join data within an integrated visual pipeline of activities with a simple drag-and-drop interface.
Quick operationalization of analytical models
Operationalizes models quickly using automated techniques in just a few clicks – in batch and real time. A repeatable framework enables easy registration, validation, tracking, monitoring and retraining of analytical models to ensure they’re performing well.
Seamless integration
Uses advanced data management and powerful in-memory capabilities to integrate with your existing transaction monitoring platform. Works with your existing AML solutions, so there's no need to replace your current platform.
Easy-to-use analytics
Lets you visually explore and evaluate segments for further analysis using k-means clustering, scatter plots and detailed summary statistics. Use advanced machine learning techniques to build and refine predictive models to target specific groups or segments, run numerous what-if scenarios simultaneously, and process results for each group or segment without having to sort or index data each time.
AML optimization
Performs intelligent customer segmentation, entity resolution and scenario threshold tuning with above-the-line/below-the-line testing to generate more productive alerts, identify “true positives” and optimize overall transaction monitoring processes.
Cloud-native, elastic & scalable
Runs on SAS® Viya®, an elastic, scalable platform for public and private clouds. Rapidly processes large data sets and accelerate the complex analytics life cycle, from data preparation to discovery to deployment. The elasticity of compute and data environments supports growth in transaction volumes and complexity of model validation.
Related Offerings
Check out these products and solutions related to SAS Financial Crimes Analytics.