Advanced Settings

Last modified: September 30, 2021

Docs are available before the release of Alteryx Machine Learning so you can get a sneak peek. This content might change between now and the official release.

The Advanced settings allow you to make detailed changes to Alteryx Machine Learning, like specific choices for automated feature engineering.

Only experienced users should change the Advanced settings.

General

The General tab contains options that allow you to tune the automated machine learning process. Make sure to select Save Settings if you make any changes.

Metric

The Metric is the objective function you want to use to determine the ranking of models you've trained. Objective functions are measures of how optimal a model is for your use-case. To learn more about specific metrics, select the book icon in the header or Learn More while on the Leaderboard panel during the Auto Model stage.

Search Limits

By default, we search until we find the best model for your use-case. Use this option to limit the search, either by duration or by the number of iterations.

Cross Validation

Choose how many folds to use during cross-validation. You can also change the percentage of holdout data.

Ensembling

Choose whether you want to use ensembling when building models. When enabled, we combine many models to create the optimal model for your use-case.

Feature Engineering

The Feature Engineering tab contains options that allow you to choose what features you want to us to automatically create using primitives.

To exclude primitives, check the boxes associated with them, then select Save Settings.

Was This Page Helpful?

Running into problems or issues with your Alteryx product? Visit the Alteryx Community or contact support. Can't submit this form? Email us.