Interface Overview: Scoring Configuration in BaseModel

The Scoring Configuration interface in BaseModel allows users to define and manage settings related to model scoring. This section provides an overview of the selected model, scoring audience, schedule, and output destination.

1. Navigation and Controls

Purpose:

Allows users to navigate between different sections of the scoring configuration and take actions.

Key Components:

• Tabs:

  • Metrics: Displays performance metrics and results from previous scoring runs.
  • Settings: The current tab, where users configure scoring parameters.
  • Logs: Shows logs related to scoring execution.

• Actions (Top Right Corner):

  • Learn More: Provides access to documentation and guides.
  • Run Now: Immediately executes the scoring based on the current configuration.
  • Activate: Finalizes the configuration and enables the scoring run.

2. Fine-tuned Model

Purpose:

Displays the selected model used for scoring.

Key Components:

• Model Name: Identifies the fine-tuned model selected for scoring
• Task: Describes the type of task performed by the model (e.g., Classification - Multilabel).

3. Scoring Audience

This section enables you to apply our Audience Filter to restrict scoring to a specific group of entities. If you prefer to score all entities included in the training, you can simply skip this section.

For limiting the audience you need to follow these steps:

1. Click on Define filter button

2. Define the logic and conditions for your entities. For instance, let's assume we want to score only clients who have never purchased jeans, as we intend to target them for a jeans campaign (focusing on those with the highest propensity). We can achieve this by setting a filter as follows:

   
   1. Select Transactions from data source
   2. Select from joined columns the Articles.product_type_name equal to 'Jeans'
   3. Apply

4. Scoring Schedule

📘

Please note

Scoring considers all available data each time it is run. For example, if you trained your models a week ago, running predictions now will incorporate all new events along with the historical data.

In this section, you define how often should your model be scored. Available options:

1. One-time scoring - for generating a single set of predictions.
2. Continuous scoring - for repeated scoring according to your defined schedule.

5. Scoring Output

In order to save the predictions, you need to eitther create a new table in Snowflake or use an existing one, all using our built-in interface: