Willekeurig onder-samplen

Fraudedetectie in R

Bart Baesens

Professor Data Science at KU Leuven

Willekeurig onder-samplen (RUS)

class_barplot_under

orig_data_train_test

random_undersampling_v0

random_undersampling_v1

creditcard_V2vsV1_version2

table(creditcard$Class)

    0     1 
24108   492

n_fraud <- 492
new_frac_fraud <- 0.50
new_n_total <- n_fraud / new_frac_fraud ## = 492 / 0.50 = 984

library(ROSE)
undersampling_result <- ovun.sample(formula = Class ~ ., data = creditcard,
                                    method = "under", N = new_n_total, seed = 2018)

undersampled_credit <- undersampling_result$data

prop.table(table(undersampled_credit$Class))

  0   1 
0.5 0.5

creditcard_V2vsV1_undersampled

Laten we beide doen!

class_barplot_both

n_new <- nrow(creditcard) ## = 24600
fraction_fraud_new <- 0.50

sampling_result <- ovun.sample(formula = Class ~ ., data = creditcard,
                               method = "both",
                               N = n_new,
                               p = fraction_fraud_new,
                               seed = 2018)

sampled_credit <- sampling_result$data

prop.table(table(sampled_credit$Class))

        0         1 
0.5039837 0.4960163

creditcard_V2vsV1_both

Laten we oefenen!

Fraudedetectie in R