From a0f98c076c4db4adf0fb652b6d96b752f39216ae Mon Sep 17 00:00:00 2001 From: Matteo Meucci Date: Thu, 6 Nov 2025 14:59:33 +0100 Subject: [PATCH] Update AITG-MOD-06_Testing_for_Robustness_to_New_Data.md --- .../tests/AITG-MOD-06_Testing_for_Robustness_to_New_Data.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Document/content/tests/AITG-MOD-06_Testing_for_Robustness_to_New_Data.md b/Document/content/tests/AITG-MOD-06_Testing_for_Robustness_to_New_Data.md index b31acdd..fde28bb 100644 --- a/Document/content/tests/AITG-MOD-06_Testing_for_Robustness_to_New_Data.md +++ b/Document/content/tests/AITG-MOD-06_Testing_for_Robustness_to_New_Data.md @@ -28,7 +28,7 @@ This test identifies vulnerabilities associated with the lack of robustness to n - **Periodically Retrain the Model**: Schedule regular retraining of the model on fresh data that includes recent production data. This ensures the model stays up-to-date with the latest data distributions. - **Domain Adaptation Techniques**: If you anticipate specific types of drift, use domain adaptation techniques during training to explicitly teach the model to be invariant to those changes. -### Suggested Tools for this Specific Test +### Suggested Tools - **DeepChecks**: An open-source Python library for validating and testing ML models and data, with a strong focus on detecting data drift, corruption, and other issues. - Tool Link: [DeepChecks on GitHub](https://github.com/deepchecks/deepchecks) - **Evidently AI**: An open-source Python library for evaluating, testing, and monitoring ML models in production. It provides interactive reports on data drift and model performance.