Variables: Features and Targets - Teradata Vantage

ClearScape Analytics™ ModelOps User Guide

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
7.1
Published
December 2024
ft:locale
en-US
ft:lastEdition
2024-12-13
dita:mapPath
zdn1704469623418.ditamap
dita:ditavalPath
azq1671041405318.ditaval
dita:id
rgn1654191066978
lifecycle
latest
Product Category
ClearScape

Features are the basic building blocks of datasets. The quality of the features in your dataset affects the quality of the insights you will gain when you use that dataset for training and evaluating models. Datasets track all activity from a job: model training, mode evaluation, and model training.

Predictions (or targets) are the variables used to train the model or evaluate the accuracy and precision, in combination with the rest of the dataset features. For training and evaluation purposes, the features and targets data must be historical and curated.

Property Description
Name Specifies the name of the variable.
Group Specifies the group the variable belongs to.
Type Specifies the data type of variable as Continuous or Categorical.
Importance (Applicable for features) Measures the increase in the prediction error of the model after the feature's values are permuted, which breaks the relationship between the feature and the true outcome.
The importance of a feature is measured by calculating the increase in the model's prediction error after permuting the feature.
  • A feature is important if shuffling its values increases the model error, because in this case the model relied on the feature for the prediction.
  • A feature is unimportant if shuffling its values leaves the model error unchanged, because in this case the model ignored the feature for the prediction.