Skip to content

8. Discover and Create Features with FeatureByte Copilot

FeatureByte offers two primary methods for feature creation:

In this tutorial, we'll focus on automatic feature creation using FeatureByte Copilot.

Note

If you want to learn how to manually create features, please consult our SDK tutorials.

Step 1: Select Your Use Case

Navigate to Feature Ideation from the Create section of the menu.

Choose the use case: "In-Store Prediction of Customer Spending on a given Product Group next 2 Weeks".

Name

Step 2: Run Semantics Detection

Click "Run Semantics Detection" to let FeatureByte identify and tag relevant tables and data columns.

Name

If the columns aren’t tagged correctly, check the suggested tags and make adjustments.

Name

Note

The accuracy of suggestions improves with more detailed data descriptions. Refer to our tutorial "Add descriptions and Tag Semantics" to update table and columns descriptions.

Step 3: Initiate Feature Ideation

Start the Feature Ideation process by clicking "Start Feature Ideation".

Step 4: Evaluate Feature Engineering Strategy

Review Copilot’s data aggregation and filtering suggestions.

Note

Not all use cases require filtering. In some scenarios, like the one in this example, filtering might be unnecessary.

Filtering becomes relevant when specific types of columns, such as "event type" and "event status," are present. For instance, in Credit Card Transactions, you might encounter columns indicating transaction type (e.g., "Purchase", "Cash Advance", "Reversal", ...) and transaction status (e.g., "Authorized", "Rejected", "Cancelled"). In such cases, Generative AI will recommend filters that are pertinent to the specific use case.

Name

Optionally, choose an appropriate Observation Table for improved data evaluation:

  1. If you created the "CUSTOMER_x_PRODUCTGROUP_Sum_of_TotalCost_next_2_weeks" target with the SDK, use the "In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2022_10K" table.
  2. If you didn't create the target using the SDK, opt for the "In_Store_Customer_x_ProductGroup_2022_10K" table.

Name

Step 5: Get Automated Feature Suggestions

Click "Start" to initiate the feature search.

Name

Review the suggested features. New features are marked as "New" in the "Readiness" column.

Name

Step 6: Evaluate and Add Features to Catalog

Filter and select features by their relevance score (e.g., score equal to 9) from Generative AI.

Name

Save your chosen features as a feature list.

Name

The features are then automatically saved as "Draft" as shown in the "Readiness" column.

Name

Reset filter.

Name

Explore features by signal type, like "diversity".

Name

Step 7: Review specific feature details

Examine specific feature details and download its notebook for further evaluation.

Name

Name

Run the feature's notebook to add it to the Catalog.

Name

Step 8: Add Multiple Features

To add a large number of features simultaneously:

  1. Clear any previous selection: Click the red cross left to the count of features selected.
  2. Filtering: Choose features by a certain criterion (e.g., relevance score of 8).
  3. Display Settings: Increase the number of rows per page (e.g., to 100).
  4. Selection: Pick features across multiple pages to add to the Catalog.

Name

Name

Name

Name

Starting a New Feature Ideation

To explore adjusted semantics, windows, or filters:

  • Click "New Feature Ideation" to begin a fresh ideation process.

Name