td-decision-tree

To build a decision tree model in Teradata Vantage, you use SQL scripts to automate data preprocessing, feature engineering, model training, and evaluation directly within the database for categorical prediction.

Yes, you can automate customer churn prediction in Teradata by analyzing historical customer data and generating SQL scripts that handle the entire workflow from feature engineering to model evaluation.

In-database machine learning for categorical prediction trains models like decision trees directly where the data resides, such as in Teradata Vantage, eliminating the need to move data externally for processing.

Yes, the td-decision-tree skill recommends and applies data preprocessing and feature engineering steps automatically before training the TD_DecisionTree classification model.

Using decision trees in SQL limits you to the classification algorithms natively supported by Teradata Vantage, requiring structured data and SQL knowledge to execute the analytical workflows.

You evaluate a TD_DecisionTree model by using the generated SQL scripts to run predictions on your data and assess the model's performance directly within the Teradata Vantage environment.