cross-validation
/ˌkrɒs ˌvælɪˈdeɪʃən/
Evaluating models by training on subsets and testing on the rest
cross-validation in a sentence
“Cross-validation revealed the model's true generalization performance.”
Origin of cross-validation
From Latin crux (cross) + validus (strong, effective), from valere (to be strong)
Related Words
precision
The proportion of positive predictions that are correct
recall
The proportion of actual positives correctly identified
F1 score
The harmonic mean of precision and recall
ROC curve
A graph showing classifier performance at various thresholds
AUC
Area Under the Curve, measuring overall model performance
confusion matrix
A table showing prediction results versus actual values