R-Squared (Coefficient of Determination)
A regression metric that indicates what proportion of the variance in the target variable is explained by the model, ranging from 0 (no explanation) to 1 (perfect prediction).
Interpretation
R^2 = 1 - (sum of squared residuals / total sum of squares). R^2 = 0.85 means the model explains 85% of the variance. Negative values indicate the model is worse than predicting the mean.
Cautions
R^2 always increases with more features (use adjusted R^2 instead). High R^2 doesn't guarantee good predictions. Can be misleading for non-linear relationships or when the variance is low.