Bosques Aleatorios - Customer Churn
Jesús Gerardo Solano Díaz A00228155
2026-02-25
Teoría
Bosques Aleatorios: son un algoritmo de aprendizaje automático supervisado, utilizado para clasificación y regresión, que combina múltiples árboles de decisión entrenados con subconjuntos aleatorios de datos (bagging).
Instalar paquetes y llamar librerías
#install.packages("caret")
library(caret)
#install.packages("randomForest")
library(randomForest)Importar la base de datos
churn <- read.csv("/Users/gerardo/Conexión de interfaces/Conexión de interfaces/customer_churn.csv")
head(churn)## CustomerID Age Gender Tenure Usage.Frequency Support.Calls Payment.Delay
## 1 2 30 Female 39 14 5 18
## 2 3 65 Female 49 1 10 8
## 3 4 55 Female 14 4 6 18
## 4 5 58 Male 38 21 7 7
## 5 6 23 Male 32 20 5 8
## 6 8 51 Male 33 25 9 26
## Subscription.Type Contract.Length Total.Spend Last.Interaction Churn
## 1 Standard Annual 932 17 1
## 2 Basic Monthly 557 6 1
## 3 Basic Quarterly 185 3 1
## 4 Standard Monthly 396 29 1
## 5 Basic Monthly 617 20 1
## 6 Premium Annual 129 8 1Entender la base de datos
summary(churn)## CustomerID Age Gender Tenure
## Min. : 2 Min. :18.00 Length:440833 Min. : 1.00
## 1st Qu.:113622 1st Qu.:29.00 Class :character 1st Qu.:16.00
## Median :226126 Median :39.00 Mode :character Median :32.00
## Mean :225399 Mean :39.37 Mean :31.26
## 3rd Qu.:337739 3rd Qu.:48.00 3rd Qu.:46.00
## Max. :449999 Max. :65.00 Max. :60.00
## NA's :1 NA's :1 NA's :1
## Usage.Frequency Support.Calls Payment.Delay Subscription.Type
## Min. : 1.00 Min. : 0.000 Min. : 0.00 Length:440833
## 1st Qu.: 9.00 1st Qu.: 1.000 1st Qu.: 6.00 Class :character
## Median :16.00 Median : 3.000 Median :12.00 Mode :character
## Mean :15.81 Mean : 3.604 Mean :12.97
## 3rd Qu.:23.00 3rd Qu.: 6.000 3rd Qu.:19.00
## Max. :30.00 Max. :10.000 Max. :30.00
## NA's :1 NA's :1 NA's :1
## Contract.Length Total.Spend Last.Interaction Churn
## Length:440833 Min. : 100.0 Min. : 1.00 Min. :0.0000
## Class :character 1st Qu.: 480.0 1st Qu.: 7.00 1st Qu.:0.0000
## Mode :character Median : 661.0 Median :14.00 Median :1.0000
## Mean : 631.6 Mean :14.48 Mean :0.5671
## 3rd Qu.: 830.0 3rd Qu.:22.00 3rd Qu.:1.0000
## Max. :1000.0 Max. :30.00 Max. :1.0000
## NA's :1 NA's :1 NA's :1str(churn)## 'data.frame': 440833 obs. of 12 variables:
## $ CustomerID : int 2 3 4 5 6 8 9 10 11 12 ...
## $ Age : int 30 65 55 58 23 51 58 55 39 64 ...
## $ Gender : chr "Female" "Female" "Female" "Male" ...
## $ Tenure : int 39 49 14 38 32 33 49 37 12 3 ...
## $ Usage.Frequency : int 14 1 4 21 20 25 12 8 5 25 ...
## $ Support.Calls : int 5 10 6 7 5 9 3 4 7 2 ...
## $ Payment.Delay : int 18 8 18 7 8 26 16 15 4 11 ...
## $ Subscription.Type: chr "Standard" "Basic" "Basic" "Standard" ...
## $ Contract.Length : chr "Annual" "Monthly" "Quarterly" "Monthly" ...
## $ Total.Spend : num 932 557 185 396 617 129 821 445 969 415 ...
## $ Last.Interaction : int 17 6 3 29 20 8 24 30 13 29 ...
## $ Churn : int 1 1 1 1 1 1 1 1 1 1 ...churn <- na.omit(churn
)
churn$Churn <- as.factor(churn$Churn)
churn$Contract.Length <- as.factor(churn$Contract.Length)
churn$Subscription.Type <- as.factor(churn$Subscription.Type)
churn$Gender <- as.factor(churn$Gender) Partir datos 80/20
set.seed(123)
data_entrenamiento <- createDataPartition(churn$Churn, p=0.8, list=FALSE)
entrenamiento <- churn[data_entrenamiento, ]
prueba <- churn[-data_entrenamiento, ]Modelo de Bosques Aleatorios
modelo <- randomForest(Churn ~ . -CustomerID, data = entrenamiento, ntree = 100, importance = TRUE)
resultado_entrenamiento <- predict(modelo, entrenamiento)
resultado_prueba <- predict(modelo, prueba)Matrices de Confusión
# Matriz de Confusión del Resultado del Entrenamiento
mcre <- confusionMatrix(resultado_entrenamiento, entrenamiento$Churn)
mcre## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 152667 0
## 1 0 200000
##
## Accuracy : 1
## 95% CI : (1, 1)
## No Information Rate : 0.5671
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Sensitivity : 1.0000
## Specificity : 1.0000
## Pos Pred Value : 1.0000
## Neg Pred Value : 1.0000
## Prevalence : 0.4329
## Detection Rate : 0.4329
## Detection Prevalence : 0.4329
## Balanced Accuracy : 1.0000
##
## 'Positive' Class : 0
## # Matriz de Confusión del Resultado de la Prueba
mcrp <- confusionMatrix(resultado_prueba, prueba$Churn)
mcrp## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 38165 7
## 1 1 49992
##
## Accuracy : 0.9999
## 95% CI : (0.9998, 1)
## No Information Rate : 0.5671
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.9998
##
## Mcnemar's Test P-Value : 0.0771
##
## Sensitivity : 1.0000
## Specificity : 0.9999
## Pos Pred Value : 0.9998
## Neg Pred Value : 1.0000
## Prevalence : 0.4329
## Detection Rate : 0.4329
## Detection Prevalence : 0.4330
## Balanced Accuracy : 0.9999
##
## 'Positive' Class : 0
## Resultados
plot(modelo)
varImpPlot(modelo)
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