MachineLearning (version 0.1.4)

CREA.RBS: An expert rule based system using Reduction Based on Significance

Description

CREA-RBS is a rule reduction method for allocating a significance value to each rule in the system so that experts may select the rules that should be considered as preferable and understand the exact degree of correlation between the different rule attributes.

Arguments

formula

a formula of the form y ~ x1 + x2 + ...

data

the data frame that contains the variables specified in formula.

Value

A MLA object of subclass CREA-RBS

Details

Significance is calculated from the antecedent frequency and rule frequency parameters for each rule; if the first one is above the minimal level and rule frequency is in a critical interval, its significance ratio is computed by the algorithm. These critical boundaries are calculated by an incremental method and the rule space is divided according to them. The significance function is defined for these intervals.

References

Almi<U+00F1>ana, M., Escudero, L. F., P<U+00E9>rez-Mart<U+00ED>n, A., Rabasa, A., & Santamar<U+00ED>a, L. (2014). A classification rule reduction algorithm based on significance domains. Top, 22(1), 397-418.

Examples

# NOT RUN {
## Load a Dataset
data(EGATUR)
## Generate a CREA-RBS model, remmember only support discretized variables
CREA.RBS(GastoTotalD~pais+aloja+motivo,data=EGATUR)



# }