SAS^® Model Manager

SAS^® MODEL MANAGER

Streamline analytical model deployment and management.

SAS is a Leader in The Forrester Wave™: Multimodal Predictive Analytics and Machine Learning, Q3 2020.

Register SAS and open source models within projects or as standalone models. Develop and validate candidate models. Assess and compare candidate models for champion model selection. Then publish and monitor champion and challenger models to ensure optimal model performance.

Centralized model repository

Easily manage analytical models via a centralized, secure web-based repository. Prebuilt model life cycle templates let you manage projects collaboratively.

Analytical workflow management

Define and track custom workflows for model life cycle management, including all phases – from problem-statement creation to model development and utilization.

Model validation

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.

Performance monitoring and reporting

Automatically monitor and report on model performance during test and production cycles. Templates document the validation performance and sign-off process, and an audit trail is created when the champion model is marked for production and the predecessor is retired.

Easily register, publish, score, monitor, retrain and govern your analytical models to get value from data.

Quickly operationalize your analytical models.

SAS Model Manager simplifies model collection creation and management with a web-based interface that easily automates the model management process. It also facilitates more effective collaboration by letting users track progress through each step of the modeling process. Rapid, automated techniques let you operationalize models with just a few clicks, both in batch and in real time. A repeatable framework enables easy registration, validation, tracking, monitoring and retraining of analytical models to ensure they’re performing well. You can define customized workflows for different model types, and everyone involved in interacting with or interpreting models gets a unified view of each model’s currency, definition and function.

Keep your models performing at their highest levels.

Easily test and compare analytical models with a web-based interface that ensures more efficient model processing and governance. Performance benchmarking reports and alerts can be generated for easy tracking to indicate model decay. Extensive tracking, validation and auditing reports are produced as analytical models are used across different departments and marked as champions for use in other applications. 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.

Ensure transparency and analytics governance.

The centralized model repository, life cycle templates and version control provide visibility into your analytical processes, ensuring complete traceability and analytics governance. It enables effective collaboration by letting users track progress through each step of the model management process, and everyone involved gets a unified view of each model’s currency, definition and value.

Gain complete knowledge of your model collections.

Track models from creation, through usage, to retirement with a centralized, efficient, repeatable process for registering, validating, monitoring and retraining models. Whenever a version is created, a snapshot of model properties and files is captured, ensuring comprehensive version control. Models are secured, and model version history is locked down and retained.