AI GLOSSARY · DATA & ML
Train/test split
Keeping some data aside, unseen during training, to measure real performance.
Example
Train on 80% of records, test on the other 20%.
Learn it by doing
Reading a definition is a start; using the idea makes it stick.
Related terms
DATA & MLBaselineA simple reference result that a model must beat to be worth using.DATA & MLOverfittingWhen a model memorises training data and performs poorly on new data.DATA & MLData leakageWhen information from the test set or the future sneaks into training, making results look better than they are.DATA & MLClassificationPredicting a category, such as spam or not spam.DATA & MLRegressionPredicting a number, such as a price or a quantity.DATA & MLClusteringGrouping similar items without predefined labels.