Classification in statistical or machine learning models refers to description of the relationship between a dependent variable (outcome variable) and independent variables (features) in data sets when comparing discrete values (integers, enumerations, strings, text vectors, etc.), as opposed to scalar (continuously variable) real numbers.
Machine learning classification algorithms assign categories to data set members based on the models built from training data. Binary classification models predict “yes-no” or “in-out” for each row when there are only two choices (classes) of independent variable. Multi-variate, or multinomial, classification models predict the probability that a data set member is in one of three or more classes.