Glossary term
Glossary term
Foundations
A model's ability to make correct predictions on new, previously unseen data. A model that can generalize is the opposite of a model that is overfitting.
Click the icon for additional notes.
See Generalization in Machine Learning Crash Course for more information.
Created for this library
An ML team monitors generalization by comparing training and validation loss to spot overfitting before it shows up in production.
A pricing team selects models that generalize across regions rather than the single model with the best training loss on one market.
A risk modeling team prioritizes generalization to out-of-time data because the production environment will always face newer applications than training.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License