SAS^® Financial Crimes Analytics

SAS Financial Crimes Analytics Features List

Data exploration & visualization

Self-service data preparation.
Import your own data, join tables and apply basic data quality functions with easy drag-and-drop capabilities.
Interact with data visually – to add or change variables, remove outliers, etc.

Use machine learning techniques to build predictive models from a user-friendly visual or programming interface.
Concurrently build models and process results for each group or segment without having to sort or index data each time.

Validate model scoring logic before models are pushed into production using a precise methodology and a system that automatically records each test the scoring engine performs.
Explore and compare multiple approaches rapidly to find the optimal parameter settings for diverse machine learning algorithms – including decision trees, random forests, gradient boosting, neural networks, support vector machines and factorization machines – by simple selection of the option.

Drag and drop functionality, best practice templates, simple merge and split features, automatic rule generation and one-click model deployment.
Register, validate, track, monitor and retrain analytical models using a repeatable framework to ensure they’re performing well.
Define customized workflows for different model types and provide a unified view of each model’s currency, definition and function to those involved in interacting with or interpreting the models.

Test and compare analytical models with a web-based interface that ensures more efficient model processing and governance.
Track model decay with performance benchmarking reports and alerts.
Identify when it’s necessary to refine or retire a model with ongoing monitoring.
Integrate model retraining with the model pipeline processing environment for increased efficiency.

Gain a holistic view of risk by visualizing complete customer networks and rapidly uncovering complex, hidden relationships for deeper investigations.
Visualize and interactively explore an entity’s entire social network and its layout.

Sift through growing volumes of text data to identify main ideas or topics, extract key terms, analyze sentiment, and identify correlations between words with the right combination of natural language processing, machine learning and deep learning methods and linguistic rules.
Automatically detect relationships and sentiment in text data, eliminating time-consuming manual analysis with intelligent algorithms and NLP techniques.

Identify, investigate and act on suspicious activities quickly and easily with self-service capabilities that govern the complete life cycle of an investigation.

Apply supervised machine learning algorithms to prioritize alerts that warrant investigation and hibernate low-value alerts.

Perform scenario effectiveness, what-if simulation, above-the-line/below-the-line threshold tuning and ad hoc lookbacks using statistical methods and advanced analytical processes.

Cloud-enabled and open analytics engine.
Cohesive environment for all analytical tasks, including data access, preparation, interactive exploration, optimization, machine learning, AI, advanced model development and deployment activities.
Centralize the management of all open source and SAS models, lineage and templates, giving you full visibility and control over all your modeling activities.