Treatment learning is a process by which an ordered classified data set can be evaluated as part of a data mining session to produce a representative data model. The data model should describe some key property of the data set. The output of a treatment learning session is a treatment, a conjunction of attribute-value pairs. The size of the treatment is the number of pairs that compose the treatment. From: Three concepts can be used to define treatment learning: lift, minimum best support, and treatment effect size.