Z-Score Normalization
A standard data scaling technique that centers a feature's distribution around a mean of exactly zero with a standard deviation of exactly one.
Think of It Like This
Like converting everyone's test scores from raw points into a percentage above or below the class average so you can compare them fairly.
Also called Standardization, it subtracts the mean and divides by the standard deviation for every data point. This ensures that features measured in completely different units (like age in years vs. salary in dollars) contribute equally to the model's loss function. It is a strictly mandatory preprocessing step for distance-based algorithms and neural networks.