Random Forest Analysis

The Random Forest analysis techniques was used to improve prediction on the German Credit Dataset.

The dataset is found:

url="http://freakonometrics.free.fr/german_credit.csv"
credit=read.csv(url, header = TRUE, sep = ",")

str(credit)

## 'data.frame':    1000 obs. of  21 variables:
##  $ Creditability                    : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ Account.Balance                  : int  1 1 2 1 1 1 1 1 4 2 ...
##  $ Duration.of.Credit..month.       : int  18 9 12 12 12 10 8 6 18 24 ...
##  $ Payment.Status.of.Previous.Credit: int  4 4 2 4 4 4 4 4 4 2 ...
##  $ Purpose                          : int  2 0 9 0 0 0 0 0 3 3 ...
##  $ Credit.Amount                    : int  1049 2799 841 2122 2171 2241 3398 1361 1098 3758 ...
##  $ Value.Savings.Stocks             : int  1 1 2 1 1 1 1 1 1 3 ...
##  $ Length.of.current.employment     : int  2 3 4 3 3 2 4 2 1 1 ...
##  $ Instalment.per.cent              : int  4 2 2 3 4 1 1 2 4 1 ...
##  $ Sex...Marital.Status             : int  2 3 2 3 3 3 3 3 2 2 ...
##  $ Guarantors                       : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ Duration.in.Current.address      : int  4 2 4 2 4 3 4 4 4 4 ...
##  $ Most.valuable.available.asset    : int  2 1 1 1 2 1 1 1 3 4 ...
##  $ Age..years.                      : int  21 36 23 39 38 48 39 40 65 23 ...
##  $ Concurrent.Credits               : int  3 3 3 3 1 3 3 3 3 3 ...
##  $ Type.of.apartment                : int  1 1 1 1 2 1 2 2 2 1 ...
##  $ No.of.Credits.at.this.Bank       : int  1 2 1 2 2 2 2 1 2 1 ...
##  $ Occupation                       : int  3 3 2 2 2 2 2 2 1 1 ...
##  $ No.of.dependents                 : int  1 2 1 2 1 2 1 2 1 1 ...
##  $ Telephone                        : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ Foreign.Worker                   : int  1 1 1 2 2 2 2 2 1 1 ...

convert categorical variables as factors,

F=c(1,2,4,5,7,8,9,10,11,12,13,15,16,17,18,19,20)
for(i in F) credit[,i]=as.factor(credit[,i])

create our training/calibration and validation/testing datasets, with proportion 1/3-2/3

i_test=sample(1:nrow(credit),size=333)
i_calibration=(1:nrow(credit))[-i_test]

LogisticModel <- glm(Creditability ~ Account.Balance + Payment.Status.of.Previous.Credit + Purpose + 
Length.of.current.employment + 
Sex...Marital.Status, family=binomial, 
data = credit[i_calibration,])

fitLog <- predict(LogisticModel,type="response", newdata=credit[i_test,])

library(ROCR)

## Warning: package 'ROCR' was built under R version 3.3.3

## Loading required package: gplots

## 
## Attaching package: 'gplots'

## The following object is masked from 'package:stats':
## 
##     lowess

## Loading required package: methods

pred = prediction( fitLog, credit$Creditability[i_test])
perf <- performance(pred, "tpr", "fpr")
plot(perf)

AUCLog1=performance(pred, measure = "auc")@y.values[[1]]
cat("AUC: ",AUCLog1,"n")

## AUC:  0.7340226 n

Alternative is to consider a logistic regression on all explanatory variables

LogisticModel <- glm(Creditability ~ ., family=binomial, data = credit[i_calibration,])
fitLog <- predict(LogisticModel,type="response",newdata=credit[i_test,])
pred = prediction( fitLog, credit$Creditability[i_test])
perf <- performance(pred, "tpr", "fpr")
plot(perf)

AUCLog2=performance(pred, measure = "auc")@y.values[[1]]
cat("AUC: ",AUCLog2,"n")

## AUC:  0.7532581 n

Regression tree method

library(rpart)
ArbreModel <- rpart(Creditability ~ ., data = credit[i_calibration,])

library(rpart.plot)

## Warning: package 'rpart.plot' was built under R version 3.3.3

prp(ArbreModel,type=2,extra=1)

fitArbre <- predict(ArbreModel, newdata=credit[i_test,],type="prob")[,2]
pred = prediction( fitArbre, credit$Creditability[i_test])
perf <- performance(pred, "tpr", "fpr")
plot(perf)

AUCArbre=performance(pred, measure = "auc")@y.values[[1]]
cat("AUC: ",AUCArbre,"n")

## AUC:  0.719152 n

Random Forest analysis

library(randomForest)

## Warning: package 'randomForest' was built under R version 3.3.3

## randomForest 4.6-12

## Type rfNews() to see new features/changes/bug fixes.

RF <- randomForest(Creditability ~ .,data = credit[i_calibration,])
fitForet <- predict(RF,newdata=credit[i_test,],type="prob")[,2]
pred = prediction( fitForet, credit$Creditability[i_test])
perf <- performance(pred, "tpr", "fpr")
plot(perf)

AUCRF=performance(pred, measure = "auc")@y.values[[1]]
cat("AUC: ",AUCRF,"n")

## AUC:  0.7892439 n