Ordinal attributesAn attribute whose possible values have a meaningful order or ranking, but the difference between successive values is unknown, and has a sequence and size.

Ordinal attribute application

An ordinal attribute has a meaningful order or rank for its possible values, but the differences between successive values are unknown, for example:

Students' grades can be divided into four levels: excellent, good, medium, and poor; grades include A+, A, A-, B+, B, etc.; the beverage cups in a fast food restaurant have three possible values: large, medium, and small, but it is unknown how much larger "large" is than "medium".

Ordinal attributes can be used to record quality assessments that cannot be objectively measured and can therefore be used in rating surveys, for example:

Evaluation of the customer service quality of the sales department, 0 means very dissatisfied, 1 means not very satisfied, 2 means neutral, 3 means satisfied, and 4 means very satisfied.

Ordinal attribute characteristics

Through data reduction in data preprocessing, the ordinal attribute can divide the value range of the data into a finite number of ordered categories and discretize the numerical attributes. It should be noted that the ordinal attribute is qualitative and only describes the sample characteristics without giving the actual size or quantity.

Parent word: attribute