'Cross-validation' means:

k-Fold Cross-Validation (typically k=5 or 10) overcomes the limitation of a single train/test split, which can be lucky or unlucky based on which data ends up in each set. Each data point appears in the validation set exactly once. It provides k performance estimates whose average and standard deviation give a reliable picture of model performance and stability. Stratified k-Fold maintains class proportions in each fold which is important for imbalanced banking datasets as fraud cases are rare. Leave-One-Out (LOO) is an extreme case where k = n (dataset size).