AI Studio Step 4: Validation

Profiles: Model Creator, Data Scientist

As a model creator or data scientist, the fourth step in AI Studio is validation.

This page explains the validation functionality within AI Studio.

Overview

In the Validation section you can see the performance of your model tested on the ground truth.

The model gets tested only on unseen data, due to the k-fold validation approach.

Usage

All models within a project are listed in the Validation Dashboard as shown below:

Note: The Accuracy of the model is shown in the last column after the training process is finished.

Tip: To see the detailed validation of a model, click Validate.

The performance of a model is shown in the Validate Model screen. In addition to common performance metrics and the confusion matrix, there is a detailed view of text extracts that have been classified correctly or incorrectly, as shown below:

In case the performance of the trained model stays below expectations, it can be helpful to try one of the following tips:

• Try another template.

• Check which examples got miss classified and add more similar example.

• Add more examples to the ground truth.

• Try to build a successful proximity rule model first and use the bulk labeling feature to expand your ground truth set.