Getting Started with SAS Enterprise Miner for Machine Learning

Video description

This course introduces Enterprise Miner while demonstrating two common applications: segmentation and predictive modeling. It starts with a brief overview of the software and then covers segmentation and predictive modeling using a case-study approach based on real-world data. Upon completing the course, learners will have a basic, working knowledge of how to use Enterprise Miner to perform data mining and machine learning tasks. Participants should have a quantitative background and (ideally) some basic understanding of predictive models, including regression.

  • Learn how to use Enterprise Miner to perform data mining and machine learning tasks
  • Explore the fundamentals of predictive modeling and clustering
  • Discover how to build, compare, and deploy predictive models using SAS Enterprise Miner
  • Learn how to perform, interpret, and profile a cluster analysis using SAS Enterprise Miner

Jeffrey Thompson is a Senior Analytical Training Consultant with the SAS Institute and has worked with SAS since the early 90s. A former associate professor of statistics at North Carolina State University, Jeffrey has been published in the International Statistical Review, the Austrian Journal of Statistics, and other peer-reviewed journals. He holds a bachelor's degree in mathematics, a master's degree in statistical computing, and a PhD in statistics.

Table of contents

  1. Chapter 1: Introduction
    1. Welcome to the Course
    2. About the Author
  2. Chapter 2: Introduction to SAS Enterprise Miner
    1. The Enterprise Miner Interface
    2. The SEMMA Approach
    3. Analytical Workflow and Enterprise Miner Strengths
  3. Chapter 3: Accessing and Assaying Prepared Data
    1. Defining a Data Source and Application for the First Demonstration
    2. Demo: Opening Enterprise Miner, Opening a Project, and Setting Sampling Preferences
    3. Demo: Creating a Data Source in Enterprise Miner
    4. Demo: Changing Metadata
    5. Demo: Exploring Data
  4. Chapter 4: Introduction to Pattern Discovery
    1. Introduction to Pattern Discovery and Applications
    2. Segmentation
    3. Demo: Opening a Diagram and bringing a Data Source into a Process Flow
    4. Demo: Filtering out Unwanted Cases
    5. Demo: Setting up and Running the Cluster Node
    6. Demo: Results of the Cluster Node
    7. Demo: Profiling the Clusters
  5. Chapter 5: Introduction to Predictive Modeling
    1. Introduction to Predictive Modeling and Application for the Second Demonstration
    2. Predictive Modeling Essentials
    3. Demo: Opening a Diagram and Exploring Data
    4. Demo: Partitioning Data
    5. Demo: Building and Discussing a Decision Tree
    6. Demo: Imputation and Setting up Regression and Neural Network Models
    7. Demo: Running Regression and Neural Network Models and Model Comparison
  6. Chapter 6: Model Implementation
    1. Model Implementation
    2. Demo: Creating a Scoring Data Source
    3. Demo: Internally Scoring New Data
    4. Demo: Exploring Exported Data
    5. Demo: SAS Score Code and Java and C Score Code
  7. Chapter 7: Conclusion
    1. Wrap Up and Thank You

Product information

  • Title: Getting Started with SAS Enterprise Miner for Machine Learning
  • Author(s): Jeff Thompson
  • Release date: February 2018
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781492028390