KDnuggets : News : 2008 : n17 : item10 < PREVIOUS | NEXT >

Webcasts

From: Bruce Ratner
Date: 8 Sep 2008
Subject: Webcasts Sep 17, 24: Genetic Regression Modeling & Data Mining with the GenIQ Model(c)

Genetic Regression Modeling & Data Mining with the GenIQ Model(c)

The GenIQ Model(c) is a machine learning alternative model to the statistical ordinary least squares and logistic regression models. GenIQ lets the data define the model -- automatically data mines for new variables, performs variable selection, and then specifies the model equation -- so as to "optimize the decile table," to fill the upper deciles with as much profit/many responses as possible. GenIQ requires no programming (though there is optional control of process), produces models that outdo statistical models, and is a different model: unsuspected equation, ungainly interpretation, and easy implementation.

Prerequisites for the GenIQ Webcast 0. MUST BE serious-minded about new, different software for Regression Modeling & Data Mining. Onlookers find the webcast trying and ultimately leave early in the webcast, disrupting the flow of the presentation for the serious-minded attendees.

1. A practiced-to-advanced modeler of statistical ordinary least squares and logistic regression models along with an understanding of how the decile table is used to assess model performance, AND who can "think out of the box," after reading Historical Notes.

OR

2. A well-informed end-user of at least one of today's many models* along with an understanding of how the decile table is used to assess model performance, AND is in earnest about an easy-to-use method that is not a "black box," but rather is transparent in its output.

  • For example: statistical, machine learning, genetic algorithms/programming, decision trees, rules-based, neural networks, bayesian, rough-sets, fuzzy-logic, and SVM.
Register for the Sep 17 Webcast

or

Register for the Sep 24 Webcast

Bookmark using any bookmark manager!


KDnuggets : News : 2008 : n17 : item10 < PREVIOUS | NEXT >

Copyright © 2008 KDnuggets.   Subscribe to KDnuggets News!