Model Selection

Hardik Chheda Updated by Hardik Chheda

After selecting the target variable, dataset, and the features, Tellius displays the model selection page where you select the model algorithm and the necessary options.

Now, specify appropriate values in the following fields:

Note: The fields on the page differs based on the type of model you select.
  • Select Model: Select the model algorithm that you want to apply for your prediction.
  • Model name: The name of the model.
  • Hyper Parameters: Turn On the parameter turning. For more information, see Hyperparameter tuning.
  • Max Depth: Maximum depth of the tree. (>=0). For example, depth 0 means 1 leaf node; depth 1 means 1 internal node + 2 leaf nodes.
  • Max bins: Max number of bins for discretizing continuous features. Must be >=2 and >= number of categories for any categorical feature.
  • Impurity: Criteria used for information gain calculation (case-sensitive). The supported option is variance.

After specifying the values, click the Next button. Tellius starts preparing the model. This process will run in background. Depending on the data size, it may take from seconds to few minutes. You can check the job status on the Notifications page.

After the model preparation is over, the Model Evaluation page appears.

How did we do?

Feature Transform

Model Evaluation