Feature Selection Transformer

Use of the Assisted Modeling tool requires participation in the Alteryx Analytics Beta program. Visit the the Alteryx beta program, also known as the Alteryx Customer Feedback Program, to find out more. All Alteryx Beta Program notifications and disclaimers apply to this content. Functionality described here may or may not be available as part of the Beta Program. To send feedback about the documentation, send an email message to helpfeedback@alteryx.com.

Feature selection: Selecting features is a type of transformer.

Use a transformer to pre-process a model and improve the performance of the model by reducing bias, defining relationships, removing outliers, and more. Apply the transformation using the Transformation tool in the Machine Learning tool palette. Transformations include setting data types, clean up of missing values, and selecting columns. Alteryx Machine Learning Transformers generate a new dataset using one or more rows or columns of your existing dataset. .

Selecting a different transformer clears any changes you might have made.

Before using the tool

Start with an existing workflow. You should first clean and prep your dataset. Once your dataset contains only the relevant data you need for your business use case, then start building a pipeline using the Machine Learning tools.

Add the tool

Click the Transformation tool in the Machine Learning tool palette. Drag it to the workflow canvas, and connect it to your workflow.
A start pipeline tool is required for the transformation to function. Your workflow should contain a start pipeline tool such as the Start Pipeline tool or the Assisted Modeling tool prior to starting a data transformation.

In Transformer, select the transformation type you want to configure.
Configure the tool.

Configure the tool

Configure the parameters. Understand the parameters before changing them. For best practices, avoid making assumptions, and use a test dataset to assess the performance of your model whether your objective is prediction or not.

To find out more about a parameter, click the parameter's tooltip.

Select the features you want to use as predictors. This transformation provides an opportunity to double-check the features in your dataset, make any changes you want, and take action to improve model performance. See Machine Learning Tools Glossary.

You should evaluate all the possible features in your dataset and decide which are most important in your model, that is, those that will most improve model performance. The most important features will be those that result in the most accurate model. There are several factors to consider.