Skip to content

10. Compute Feature Table

In this tutorial, you will learn how to generate a Feature Table from the feature lists created in previous tutorials. Once the tables are generated, you will download them and train a LightGBM model to compare their accuracy.

Step 1: Compute Feature Table

Navigate to the Feature List Catalog under the 'Experiment section of the menu.

For each feature list, follow these steps:

  1. Click Compute Icon. Name

  2. Select the Observation Table CREDIT_DEFAULT_TRAIN_2019_2023. Name

  3. Confirm the computation by clicking Compute Button. Name

  4. Repeat it with the Observation Table CREDIT_DEFAULT_HOLDOUT_2024_1H. Name

Step 2: Review Feature Table

  1. Navigate to the Feature Table Catalog under the 'Experiment section of the menu. Name
  2. Click on the Rule-based selection from Semi-Automated Mode - CREDIT_DEFAULT_TRAIN_2019_2023 table. Name
  3. Open the 'Preview' tab to examine the table Name
  4. Select individual columns by clicking on column filter. Name

Step 3: Download Feature Tables

For each table, follow these steps:

  1. Click on the table in the Feature Table Catalog to open its details.

  2. Go to the 'About' tab and click table download to download the table. Name

Step 4: Train LightGBM

To evaluate the performance of your feature lists, download the modeling pipeline for LightGBM along with the accompanying notebook that you can download here. Use the notebook to evaluate the accuracy of each feature list and determine the best-performing one.

Name

Step 5: Iterate

Now, it's your turn!

Suggestions:

  • Rerun Feature Ideation with the two additional tables available for exploration: CASH_LOAN_STATUS and CASH_INSTALLMENTS.
  • Refine the ideation process.
  • Use the SDK to customize features.