Close this search box.

Glossary of Artificial Intelligence (AI), Machine Learning (ML), and Big Data Terms

Test (“Holdout”) Data set

A data set of prepared data that is set aside from training and validation data to be used to verify that a machine learning model performs as expected against data it has not yet seen during training or validation. Test data helps verify model performance as part of the model evaluation phase of CPMAI to determine the generalization performance of a model. Also known as the “holdout” data set. Generally 20% of a prepared data set is used as the test data set.

Get Certified on the Proven Path to Success with AI, Big Data & Analytics Projects

Login Or Register


Register to View Event


Get The Test (“Holdout”) Data set


AI Best Practices

Get the Step By Step Checklist for AI Projects


Login to register for events. Don’t have an account? Just register for an event and an account will be created for you!