Tuesday, 26 March 2013

Introduction to Predictive Modeling

Analytics buzzwords are in the ascendency.  Buzzwords can reflect froth and pretension (google "buzzword bingo"), but they can also reflect real phenomena - companies are making billions off the analytic value in their data.  Statistics.com offers over a dozen courses related to analytics and data mining; a good place to start is "Introduction to Predictive Modeling".

"Introduction to Predictive Modeling" focuses on five predictive analytics techniques: k-nearest neighbors, classification and regression trees (CART), neural nets, logistic regression and multiple linear regression.  It will also cover the use of partitioning to divide the data into training data (to build a model), validation data (to assess and fine tune models) and test data (to predict the performance of the final model). For more details please visit at http://www.statistics.com/predictive_modeling/.

Who Should Take This Course:
Analysts of business data, consultants, MBAs seeking to update their knowledge of quantitative techniques, managers who want to see what predictive modeling can do, and anyone who wants a practical hands-on grounding in basic predictive modeling techniques.

Course Program:

Course outline: The course is structured as follows

SESSION 1: Introduction

  • Core ideas in data mining
  • Supervised and unsupervised learning
  • The steps in data mining
  • Preliminary steps
    • Sampling from a database
    • Pre-processing and cleaning the data
    • Partitioning the data
  • Building a model
    • An example with linear regression
  • K-nearest neighbor

SESSION 2: Classification

  • Judging the performance of classification algorithms
  • Classification trees
  • Logistic regression
  • Lift

SESSION 3: Neural nets

  • Neural nets
  • Comparing different models

SESSION 4: Prediction

  • Multiple linear regression
  • Regression trees

The instructor, Anthony Babinec, is the president of AB Analytics and served previously as Director of Advanced Products Marketing at SPSS; he worked on the marketing of Clementine and introduced CHAID, neural nets and other advanced technologies to SPSS.

Participants can ask questions and exchange comments with Dr. Phadke via a private discussion board throughout the period. The course takes place online at statistics.com in a series of 4 weekly lessons and assignments, and requires about 15 hours/week. Participate at your own convenience; there are no set times when you are required to be online.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune.

For India Registration and pricing, please visit us at www.india.statistics.com.

Call: 020 66009116


No comments: