SAS® Unified Insights MM 特征


  • 通过协作式、高度可扩展的单一环境提供基于 GUI 的数据挖掘和机器学习。
  • 提供与 R、Python、Java 和 Lua 模型的开源集成。
  • 允许您通过模型竞争来确定和部署最有效的模型。



  • 简化创建、管理、维护、部署和监视分析模型的过程。
  • 提供用于模型注册、验证、监视和再训练的框架。
  • 使您能够评估候选模型,以确定和发布最佳模型。
  • 确保可审计性和合规性。


Model registration

  • Provides secure, reliable, versioned storage for all types of models, as well as access administration, including backup and restore capabilities, overwrite protection and event logging.
  • Once registered, models can be searched, queried, sorted and filtered by attributes used to store them – type of asset, algorithm, input or target variables, model ID, etc – as well as user-defined propertied and editable keywords.
  • Add general properties as columns to the listing for models and projects, such as model name, role, type of algorithm, date modified, modified by, repository location, description, version and keywords (tags).
  • Access models and model-score artifacts using open REST APIs.
  • Directly supports Python models for scoring and publishing. Convert PMML and ONNX (using dlPy) to standard SAS model types. Manage and version R code like other types of code.
  • Provides accounting and auditability, including event logging of major actions – e.g., model creation, project creation and publishing.
  • Export models as .ZIP format, including all model file contents for movement across environments.
  • Easily copy models from one project to another, simplifying model movement within the repository. 

Analytical workflow management

  • Create custom processes for each model using SAS Workflow Studio:
    • The workflow manager is fully integrated with SAS Model Manager so you can manage workflows and track workflow tasks within the same user interface.
    • Import, update and export generic models at the folder level – and duplicate or move to another folder.
  • Facilitates collaboration across teams with automated notifications.
  • Perform common model management tasks, such as importing, viewing and attaching supporting documentation; setting a project champion model and flagging challenger models; publishing models for scoring purposes; and viewing dashboard reports.

Model scoring

  • Place a combination of Python, SAS or other open source models in the same project for users to compare and assess using different model fit statistics.
  • Set up, maintain and manage separate versions for models:
    • The champion model is automatically defined as a new version when the model is set as champion, updated or published in a project.
    • Choose challenger models to the project champion model.
    • Monitor and publish challenger and champion models.
  • Define test and production score jobs for SAS and Python models using required inputs and outputs.
  • Create and execute scoring tasks, and specify where to save the output and job history.

Model deployment

  • Depending on the use case, you can publish models to batch/operational systems – e.g., SAS server, in-database, in-Hadoop/Spark, SAS Cloud Analytic Services (CAS) Server, or to on-demand systems using Micro Analytic Score (MAS) service.
  • Publish Python and SAS models to run time containers with embedded binaries and score code files. Promote run time containers to local Docker, AWS Docker and Amazon EKS (elastic kubernetes service) environments.

Model monitoring

  • Monitor the performance of models with any type of score code. Performance reports produced for champion and challenger R, Python and SAS models include variable distribution plots, lift charts, stability charts, ROC, K-S and Gini reports with SAS Visual Analytics using performance-reporting output result sets.
  • Built-in reports display the measures for input and output data and fit statistics for classification and regression models to evaluate whether to retrain, retire or create new models. Performance reports for champion and challenger analytical models involving Python, SAS, R, etc., with different accuracy statistics are available.
  • Monitor performance of champion models for all projects using performance report definition and execution.
  • Schedule recurring and future jobs for performance monitoring.
  • Specify multiple data sources and time-collection periods when defining performance-monitoring tasks.


  • 为数据访问、混合、整形和清理提供交互式自助环境,以便为分析和报告准备数据。
  • 与您的分析管道完全集成。
  • 包括数据沿袭和自动化。



  • 为受监控与自助探索和可视化提供双模支持。
  • 支持自助服务发现、报告和分析。
  • 通过“智能算法”提供易于使用的预测分析。
  • 可通过电子邮件、Web 浏览器、MS Office 或移动设备共享报告。
  • 提供基于 Web 的集中式管理、监视和治理平台。



  • 使用 k 均值聚类、散点图和详细汇总统计,探索和评估各个段,以便做进一步分析。
  • 使用机器学习技术从可视化或编程界面构建预测模型。


Back to Top