FAQ

H2O Model Validation is an application that enables data scientists to validate the stability and robustness of a Driverless AI (DAI) model. With different validation tests, H2O Model Validation centralizes and visualizes how DAI models and data are validated for production while decreasing model degradation.

---

The below sections provide answers to frequently asked questions. If you have additional questions, send them to cloud-feedback@h2o.ai.

General

Which specific validation tests are available to analyze and experiment or dataset?

H2O Model Validation offers an array of validation tests to analyze the robustness and stability of Driverless AI (DAI) experiments. Specific validation tests are available to analyze an experiment or dataset.

Validation tests for an experiment:

• Adversarial Similarity
• Backtesting
• Drift Detection
• Size Dependency

Validation tests for a dataset:

• Adversarial Similarity
• Drift Detection

Feedback

• Submit and view feedback for this page
• Send feedback about H2O Model Validation to cloud-feedback@h2o.ai