Products & Solutions / Model Management & Monitoring

SAS® Model Manager

Create, manage, deploy, monitor and operationalize analytical models

SAS Model Manager streamlines the tedious and often error-prone steps of creating, managing and deploying analytical models, and continually verifies their accuracy and usefulness. Because analytics play an important role in business processes, it is critical that organizations reduce the likelihood of erroneous model output or incorrect interpretation of model results.

Benefits

  • Expedites the management and deployment of "best" models into production.
  • Ensures analytical models are up-to-date and accurate.
  • Enables auditability and compliance to meet regulatory requirements.
  • Streamlines analytical modeling processes to generate consistent and timely results.

Read more

Features

  • Central, secure repository for managing analytical models
  • Analytical workflow management
  • Scoring-logic validation before models are exported to production
  • Monitoring and reporting on model performance during test and production life cycles
  • Overall lifecycle management of analytical models

Read more

Screenshot

Easily perform common model management tasks such as importing and viewing models.


Screenshots

How SAS® Is Different

  • Fully integrated analytical workflow management. SAS Model Manager is the analytic process management hub. With Web-based workflow capabilities, users can easily define custom processes, manage them through to completion, foster collaboration with notifications, and establish enterprise standards for development, deployment, scoring and monitoring.
  • Dashboards help track model performance across multiple projects. With performance monitoring dashboards, you can quickly track model performance across multiple projects. Teams can focus on projects that need the most immediate attention and avoid model decay. SAS Model Manager includes an easy-to-use graphical interface for defining indicators and ranges.
  • Interoperability with third-party modeling tools. Many organizations use different technologies to build predictive models. However, they want to manage all of the predictive assets in a central repository. SAS Model Manager provides a full range of capabilities for importing and embedding models from other tools and lets you share models with other environments. This means SAS Model Manager users can register, compare, report, score and monitor models built in R software, and deploy them just like SAS models.
  • Fully integrated scoring and performance monitoring with database engines. SAS Model Manager is tightly integrated with SAS Scoring Accelerator to enable the registration and validation of in-database scoring functions within several databases (currently supported databases are Aster Data, Pivotal Greenplum Database, IBM DBS, IBM Netezza, Oracle and Teradata).
  • Scalable and repeatable mechanisms to support operational analytics. SAS Model Manager provides the ability to easily manage, deploy and fine-tune models on demand, on a set schedule or when triggered by external business events. Integrating model deployment processes with other operational processes generates consistent analytical results.

Benefits

  • Expedites the management and deployment of "best" models into production. SAS Model Manager provides an efficient and repeatable process for registering, validating, deploying, monitoring and retraining models. Accountability metrics and version control status reports track who changes what, when control is passed from one area to another, etc. Models can be monitored from their creation to deployment into real-time or batch scoring systems until they are retired.
  • Ensures analytical models are up-to-date and accurate. With its iterative framework, SAS Model Manager ensures analytical models are tested and compared, performance benchmarking reports are generated and as models are deployed, performance metrics are pushed to established reporting channels. Modelers can easily collaborate and reuse models, and automated alerts can be set to detect when the scoring results are changing over time, indicating model decay.
  • Enables auditability and compliance to meet regulatory requirements. Unique compliance and validation reporting capabilities in SAS Model Manager are highly sought-after by those facing heightened regulatory requirements. A centralized model repository, lifecycle templates and version control provide visibility into analytical processes and ensure that they can be audited to comply with internal governance and external regulations. In addition, new Basel II risk model validation reports help organizations gain transparency by assessing the soundness of internal credit risk measurement systems, tracking down anomalies and answering regulator inquiries on demand.
  • Streamlines analytical modeling processes to generate consistent and timely results. SAS Model Manager provides an easy-to-access Web-based client (the SAS Workflow Console) that provides an automated and collaborative model management process. Users can track the progress through each step of the modeling project(s), and can create multiple, customized workflows for different types of models. Different users touching or interpreting a model will get a unified view of its current stage with access to meaningful information that will help them take relevant actions.

Features

Central, secure repository for managing analytical models
  • Project-based storage of models. 
    • Set up and maintain separate versions of champion and challenger models within a project: 
      • Champion model is automatically set as a default version. One only champion model is produced per project.
      • Select challenger models to the project champion model.
      • Monitor and publish challenger and champion model packages.
    • Monitor performance of champion models for all projects within a portfolio of models and publish the models to the SAS Metadata Repository.
    • Create and manage multiple projects as a portfolio of models.
    • Map prerequisite data sources used for model reporting and score code testing.
    • Accounting and auditability:
      • Event logging of all major actions.
      • User-defined notes.
      • Ability to attach documents (Microsoft Word documents, Microsoft Excel spreadsheets, HTML files, etc.), and add version control.
  • Prebuilt templates for automatically registering standard data mining models:
    • Prediction, including models from SAS Rapid Predictive Modeler.
    • Segmentation.
    • Classification.
    • Scorecards.
    • User-defined templates.
    • Optional batch model registration support for bulk loading.
    • General properties such as model name, type of algorithm, creation and modification date, etc.
    • Advanced view of SAS® Enterprise Miner™ process flow diagram.
  • Model validation reports are provided for Basel II risk models, including probability of default (PD) and loss given default (LGD).
  • Provide more control in setting input and output variables to define the project.
  • Import multiple Base SAS, SAS/STAT®, SAS/ETS and SAS Enterprise Miner models, including training code, score logic, estimate tables, and target and input variables, and output variables.
  • Import select SAS/STAT linear models from a SAS package file (.SPK), including LOGISTIC, GENMOD, REG, GLMSELECT, GLIMMIX and MIXED.
  • Import from a SAS package file (.SPK):
    • SAS/STAT linear models: LOGISTIC, GENMOD, REG, GLMSELECT, GLIMMIX and MIXED.
    • SAS/ETS models: COUNTREG and SEVERITY.
    • SAS High-Performance Statistics models: HPBIN, HPLOGISTICS, HPREG and HPSPLIT (decision trees).
    • SAS High-Performance Data Mining models: HPBIN, HPREDUCE, HPNEURAL and HP FOREST.
  • Import and export PMML model code with inputs and outputs. Create DATA step score code for PMML models for inclusion in scoring tasks, reporting and performance monitoring.
  • Register, compare, report, score and monitor models built in R.
  • Repository metadata summary report with information such as number of models, number of scoring jobs, model-aging profiles, and frequency counts of how often each target and input variable has been used across the model portfolio.
  • Model repository can be queried by attributes used to store models such as type of algorithm, input or target variables, model creator, model ID, etc.
  • Secure, reliable model storage and access administration, including backup and restore capabilities, overwrite protection, event logging, and user authentication/access privilege administration.
Analytical workflow management
  • Create custom processes for each model using SAS Workflow Studio – a Web-based client:
    • SAS Workflow Studio is used to design the model approval process that is imported and managed through the SAS Model Manager Workflow Console.
    • Provide collaboration across teams with automated notifications.
    • Define, manage and track complete analytic life cycles.
    • Enable enterprise access and collaboration with the Web interface.
    • Increase efficiency with process management capabilities.
    • Associate milestones with activities as part of the workflow process definition.
    • Create and view reports within a workflow activity.
    • View the process flow diagram for an active workflow process.
  • Perform common model management tasks using the SAS Model Manager Workflow Console:
    • Import, view and attach supporting documentation and publish models.
    • Set a project champion model and flag challenger models.
    • Publish models for scoring purposes.
    • View dashboard reports.
Scoring-logic validation before models are exported to production
  • Define test and production score jobs using required inputs and outputs:
    • Map required inputs and outputs.
    • Add SAS code.
    • View log and results tables.
    • Create interactive graphs.
  • Scoring task scheduler:
    • Schedule scoring tasks to run at certain times and dates on available servers.
    • Specify where to save the scoring task output and view job history.
  • Export models to the SAS Metadata Repository
  • Production scoring:
    • Model Scoring Task is available in SAS Data Integration Studio and SAS® Enterprise Guide®.
  • Publish models directly to SAS Real-Time Decision Manager.
  • Publish model updates to different scoring channels:
    • Notify subscribers via email.
    • Store results to a file system or post to a corporate intranet.
  • In-database model deployment:
    • Using integration with SAS Scoring Accelerator, publish and validate scoring functions for native scoring within databases:
      • Publish model scoring files using a vendor-defined function in DB2, Pivotal (previously Greenplum) and Teradata.
      • Publish model scoring files using the SAS Embedded Process in Aster Data, DB2, Oracle, IBM Netezza and Teradata.
Monitoring and reporting on model performance during test and production life cycles
  • Model performance reports:
    • Variable distribution plots, characteristic charts, stability charts, lift charts, Receiver Operating Curve (ROC) charts, Kolmogorov-Smirnov (K-S) charts and Gini charts.
    • For prediction model function that has an interval target.
    • For champion and challenger model comparisons.
    • Full complement of Basel II back-testing reports.
  • Model comparison reports:
    • Model profile report, delta report, dynamic lift report, interval target variable report, etc.
    • Ad hoc SAS code report editor.
    • HTML, RTF, PDF and Microsoft Excel output formats.
    • Aggregated report to combine multiple reports from the Reports folder into a single report.
  • Training summary data set report showing frequency and distribution charts to validate data set variables.
  • Easy-to-use wizard for creating performance-monitoring dashboards:
    • Update all reports or update reports for projects that have new performance data.
  • Model retraining allows users to create new challenger models based on SAS Enterprise Miner models currently registered in a project, and new data and variables.
  • Perform scoring and performance monitoring on a database appliance (Teradata or Pivotal (previously Greenplum) that has been configured for use with SAS high-performance analytics products:
    • Calculate model performance statistics for classification and prediction models.
  • Support multiple SAS application servers when scoring or retraining a model or monitoring performance of champion and challenger models.
  • Schedule scoring and performance monitoring jobs to automate predictive modeling tasks.
  • Specify multiple data sources and time collection periods when defining performance monitoring tasks.
Overall lifecycle management of analytical models
  • Model lifecycle templates for collaborative project management:
    • Basic, standard, extended and user-defined.
    • Model Lifecycle Template editor for user-defined templates.
    • Task-oriented milestone completion and approval signoff.
  • Progress-completion status reports.
  • Create folders, projects and versions using macros.

Screenshots

Screenshot
Easily perform common model management tasks such as importing and viewing models.

The SAS Workflow Console uses a step-by-step process to help users perform common model management tasks such as importing and viewing models, attaching documentation and publishing models. Users can select a project champion model and optionally flag challenger models.

View Screenshot

Screenshot
SAS Model Manager's easy-to-use GUI.

Build more models faster with SAS Model Manager’s easy-to-use GUI.

View Screenshot

Screenshot
Dashboards let you track performance across multiple projects

Performance monitoring dashboards allow users to track the performance across multiple projects quickly, and enable teams to focus on projects that need the most immediate attention. The software includes an easy-to-use GUI to define the indicators and ranges.

View Screenshot

System Requirements

Host Platforms/Server Tier
  • HP/UX on Itanium: 11iv3 (11.31)
  • IBM AIX R64 on POWER architecture 7.1
  • IBM z/OS: V1R11 and higher
  • Linux x64 (64-bit): Novell SuSE 11 SP1; Red Hat Enterprise Linux 6.1; Oracle Linux 6.1
  • Microsoft Windows on x64 (64-bit):
    Desktop: Windows 7* x64 SP1; Windows 8** x64
    Server: Windows Server 2008 x64 SP2 Family; Windows Server 2008 R2 SP1 Family; Windows Server 2012 Family
  • Solaris on SPARC: Version 10 Update 9
  • Solaris on x64 (x64-86): Version 10 Update 9; Version 11
Client Tier
  • Microsoft Windows (64-bit): Windows 7* x64 SP1; Windows 8** x64
Middle Tier
  • HP/UX on Itanium
  • IBM AIX on POWER
  • Linux x64 (x86-64)
  • Microsoft Windows x64 (x86-64)
  • Solaris (SPARC and x64)
Supported Web Browsers
  • Internet Explorer 9: Windows 7 (32-bit and x64 32-bit Web browsers)
  • Internet Explorer 10: Windows 7 and Windows 8 (32-bit and x64 32-bit Web browsers)
  • Firefox 6 and up: Windows 7 and Windows 8 (32-bit and x64 32-bit Web browsers); Linux x64: RHEL 6 and SLES 11 (32-bit Web browsers)
  • Chrome 15 and up: Windows 7 and Windows 8 (32-bit and x64 32-bit Web browsers); Linux x64: RHEL 6.1 and SLES 11 SP 1 (32-bit Web browsers)

You can also review the Third-Party Support page for details about requirements of third-party software for use with SAS 9.4.

Required/Not Included Software
  • Base SAS software
  • SAS Enterprise Model Management is an inclusive bundle that contains Base SAS, SAS/STAT and SAS Enterprise Miner software

* NOTE: Windows 7 supported editions are: Professional, Ultimate and Enterprise.
** NOTE: Supported editions include: Windows 8, Windows 8 Pro, Windows 8 Enterprise.

Please consult your local SAS sales representative if you have questions about your platform requirements. Also, for more detailed information, please visit our support site at http://support.sas.com/resources/sysreq/.

Ready to learn more?

Call us at 1-800-727-0025 (US and Canada) or request more information.