Assignment 9

Objective

Predict customer attrition using the Credit Card data from the AER package, using the random forrest model.

Data Prep

• Created a new binary variable credit card 1
• Split the data (10127 observations), into training and validation datasets (70%/30% , 7137/2990)
• There are 19 predictors that can indicate customer attrition.

Variable Importance

Confusion Matrix

##                   Attrited Customer Existing Customer class.error
## Attrited Customer               939               206  0.17991266
## Existing Customer                78              5914  0.01301736

Model Accuracy

Using the validation data, it is observed that the model is able to:

• Predict correctly 81.3% of attrited customers.
• Misclassify 18.7% of existing customers as attrited customers.
• Predict correctly 98.9% of existing customers.
• Misclassify 1.1% of existing customers attrited customers.

## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## | Chi-square contribution |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  2990 
## 
##  
##                           | validation$predicted_Attrition_Flag 
## validation$Attrition_Flag | Attrited Customer | Existing Customer |         Row Total | 
## --------------------------|-------------------|-------------------|-------------------|
##         Attrited Customer |               392 |                90 |               482 | 
##                           |          1558.549 |           253.999 |                   | 
##                           |             0.813 |             0.187 |             0.161 | 
##                           |             0.936 |             0.035 |                   | 
##                           |             0.131 |             0.030 |                   | 
## --------------------------|-------------------|-------------------|-------------------|
##         Existing Customer |                27 |              2481 |              2508 | 
##                           |           299.530 |            48.815 |                   | 
##                           |             0.011 |             0.989 |             0.839 | 
##                           |             0.064 |             0.965 |                   | 
##                           |             0.009 |             0.830 |                   | 
## --------------------------|-------------------|-------------------|-------------------|
##              Column Total |               419 |              2571 |              2990 | 
##                           |             0.140 |             0.860 |                   | 
## --------------------------|-------------------|-------------------|-------------------|
## 
## 

The Financial Impact of the Model

• This model will generate a customer retention cost of $41,900.
• This model generates a customer value of $270,480 per year on average.
• The net benefit is $228,580 per 2,990 customers, resulting in $76.45 per customer.