Skip to content

Click in-app to access the full platform documentation for your version of DataRobot.

Advanced options

After importing data and selecting a target variable, the Data page appears. From this page you can click the Show advanced options link to access advanced modeling parameters.

These parameters are summarized in the following sections:

Option Description
Partitioning Set how data is partitioned for training/validation/holdout and the validation type.
External model prediction insights Bring external model(s) into the DataRobot AutoML environment, view them on the Leaderboard, and run a subset of DataRobot's evaluative insights for comparison against DataRobot models.
Train-time image augmentation Create new training images to increase the amount of training data.
Smart Downsampling Downsample the majority class for faster model build time.
Time Series Set a variety or time series-specific advanced options.
Feature Constraints Set monotonic constraints to control the influence between variables and target.
Bias and Fairness Set conditions that help calculate fairness and identify bias in a model's predictive behavior.
Additional Set additional parameters and modify values that can effect model builds.


Updated November 9, 2021
Back to top