Overview

Credit Default Dataset User Interface Tutorials

This tutorial series walks you through the entire process, using our User Interface. You’ll learn how to:

• Create a catalog.
• Define your data model.
• Structure your use cases.
• Use Ideation to generate relevant features and models.
• Create new feature lists, assess model performance, and perform comparisons to select the best model.
• Compute training data for training models outside FeatureByte.
• Manage deployment of your final solution.
• Navigate FeatureByte’s Approval Flow and version control.

Dataset Overview

In this tutorial, we'll work with the Credit Default Dataset, which provides transactional and historical data for predicting loan defaults. The dataset is composed of of seven tables:

• NEW_APPLICATION: Contains information about new loan applications submitted by clients.
• CLIENT_PROFILE: Describes the profile for each client.
• BUREAU: Lists all previous credits taken by clients from other financial institutions, as reported to the credit bureau.
• PREVIOUS_APPLICATION: Details prior loan applications made by the client.
• INSTALLMENTS_PAYMENTS: Logs monthly installments for loans at the time of payment.
• LOAN_STATUS: Captures the current status of each loan over time.
• CREDIT_CARD_MONTHLY_BALANCE: Provides monthly balance summaries for credit cards previously held by the client with the institution.

Tutorial Structure

This tutorial follows a structured, end-to-end workflow:

1. Create Catalog

Define the Data Model of the catalog

2. Register Tables

3. Register Entities

4. Set Default Cleaning Operations

5. Update Descriptions and Tag Semantics

Formulate your Use Case

6. Formulate Use Case

7. Create Observation Tables

7b. Create a Development Dataset

Ideate Features and Models

8. Ideate Features and Models

8b. Refine Ideation

Experiment

9. Create New Feature Lists and Models

10. Refit Model

Deploy Features and Models

11. Deploy and Serve

12. Manage Feature Life Cycle