Case studies: Commercial, multiple mining tasks systems: overview of SAS enterprise miner

  • Authors:
  • Kelly Sang

  • Affiliations:
  • Product Manager, Marketing Division, SAS Institute Inc., Cary, North Carolina

  • Venue:
  • Handbook of data mining and knowledge discovery
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

SAS/Enterprise Miner is a comprehensive software product that provides an end-to-end business solution for data mining. It provides a proven data mining methodology SEMMA (Sample, Explore, Modify, Model, Assess), ease-of-use capabilities, as well as a wide breadth of data mining functionality. All of the functionality needed to implement the SEMMA process is accessed through a single graphical user interface (GUI). The SEMMA process is driven by a process flow diagram (PFD), which one can modify and save. However, the GUI is designed in such a way that the business technologist with little statistical expertise can quickly and easily navigate through the SEMMA process, while the quantitative expert can go behind the scenes to fine-tune the analytical process. SAS/Enterprise Miner contains a collection of sophisticated data mining functionalities with a common user-friendly interface that enables the user to create and compare multiple models. Data mining modeling tools include decision trees, linear and logistic regression, neural networks, ensemble models memory based reasoning, two stage models, time series, principal components, as well as clustering and association rule discovery. Data preparation tools include outlier detection, variable transformations, missing data imputation, sampling, and the partitioning of data sets. Advanced visualization tools enable the user to examine large amounts of data in multidimensional histograms quickly and easily, and to compare modeling results graphically.