How SAS Enterprise Miner simplifies the data mining process

The SAS Enterprise Miner data mining tool helps users develop descriptive and predictive models, including components for predictive modeling and in-database scoring.

SAS Enterprise Miner is an advanced analytics data mining tool intended to help users quickly develop descriptive and predictive models through a streamlined data mining process.

Enterprise Miner's graphical interface enables users to logically move through the five-step SAS SEMMA approach: sampling, exploration, modification, modeling and assessment. Users can build a process flow by selecting the appropriate tab from Enterprise Miner's toolbar, and then dragging and dropping step-specific nodes onto a pallet.

Enterprise Miner supports several algorithms and techniques, including decision trees, time series, neural networks, linear and logistic regression, sequence and web path analysis, market basket analysis, and link analysis.

Enterprise Miner's client-server architecture enables business users and data analysts to collaborate and share models and other work. Client software operates on Microsoft Windows 7, 8 and 10. Server host options include the following:

  • HP-UX on Itanium 11i version 3 (11.31);
  • IBM AIX R64 on Power architecture 7.1;
  • IBM z/OS V1R12 and higher;
  • Linux x64 (64-bit), including SUSE Enterprise 11 SP1, Red Hat Enterprise Linux 6.1 and 6.7, and Oracle Linux 6.1;
  • Microsoft Windows on x64 (64-bit), including desktop Windows 7 x64 SP1, Windows 8 x64, and Windows 10 x64 or Server -- Windows Server 2008 x64 SP2 family, Windows Server 2008 R2 SP1 family, Windows Server 2012 family;
  • Solaris on Sparc version 10, update 9; and
  • Solaris on x64 (x64-x86): version 10, update 9; version 11.

Enterprise Miner features for the data mining process

SAS Rapid Predictive Modeler is a component of SAS Enterprise Miner that can run as an add-on to Microsoft Excel, enabling business users to perform predictive modeling directly from within their Excel spreadsheets. Models developed in Rapid Predictive Modeler can be customized by data analysts using Enterprise Miner.

Integration of R code. Analysts and developers who develop in the R language can integrate the models and transformations they write within an Enterprise Miner process flow.

Support for in-database and in-Hadoop scoring. When combined with a SAS Scoring Accelerator, scoring algorithms created in SAS Enterprise Miner can be deployed and executed within a database or Hadoop environment. Scoring Accelerators are available for Hadoop, Pivotal, DB2, IBM Netezza, Oracle, Teradata and SAS Scalable Performance Data Server.

SAS also offers Factory Miner, an add-on product that provides users with an automated, web-based framework to help them reduce the time needed to develop models. The product enables users to build, run and retrain multiple predictive models across business or customer segments quickly. It can also help identify a champion model.

Release 14.2 improved upon the previous version of Enterprise Miner by adding new nodes to execute code in a SAS Viya environment -- an open, cloud-ready, in-memory platform -- as part of a process flow diagram. Other enhancements include improvements to the Score node and Score Code Export nodes.

Enhancements in Factory Miner 14.2 enable users to create batch code that can be used for retraining models with updated data.

Contact SAS for pricing. Although there is no trial version of Enterprise Miner, SAS offers members of academia free use of its products through web access via its SAS OnDemand for Academics offering.

Next Steps

How predictive modeling algorithms failed during the presidential election

What role does big data play in privacy?

How to avoid these common predictive modeling pitfalls

Dig Deeper on Data science and analytics

Data Management
Content Management