Predictive Analytics Times
Predictive Analytics Times
EXCLUSIVE HIGHLIGHTS
SHARE THIS:

4 years ago
10 Practical Actions that Could Improve Your Model

   (adapted from Chapter 13 of the Handbook of Statistical Analysis and Data Mining Applications) After a first pass of training and evaluating a model, you may find you need to improve its results.  Here is a checklist of ten practical actions that I’ve found usually help: Transform real-valued inputs to be approximately Normal in distribution.  Regression, for instance, behaves better if the inputs are Gaussian; extremes have too much influence on squared-error.  For variables that are typically log-normally distributed, like income, this involves transforming the variable via a logarithm or the more general Box-Cox function. Remove outliers.  Note the

To view this content
Login OR subscribe for free

Already receive the Predictive Analytics Times emails?
As of January 2014, the Predictive Analytics Times now requires legacy email subscribers to upgrade their subscription - one time only - in order to attain a password-protected login and gain complete access.

Click here to complete this one-time subscription upgrade

  

Existing Users Log In
   
New User Registration
*Required field

Comments are closed.