Penalties Tab Lesson 13

  Penalties can be imposed on variables to reflect a reluctance to use a variable as a predictor.   N-Levels Bias Adjust ...

Optimal Model and Tree Stability Lesson 14

CART relies on the concept of prunning to create a sequence of nested models as final model candidates. Independent testing and cross validation is subsequently used to identify the optimal tree with ...

Searching for Hot Spots Lesson 15

Hot Spots are regions of modeling space that have are the richest in the event of interest. In fraud detection problems, we could be interested in identifying a set of rules that lead to a high ratio ...

Automate TargetShuffle Lesson 16

CART, TreeNet, MARS models only use Automate TargetShuffle to perform Monte Carlo shuffling (permutation) of the target. The values of the target are moved from their original rows to other rows at ...

Unsupervised learning and Cluster Analysis Lesson 17

Unsupervised learning does not begin with a target variable. Instead the objective is to find groups of similar records in the data. One can think of unsupervised learning as a form of data ...
Page 3 of 3
Load More