Objective

Predict Customer Attrition using the Credit Card data set , using the classification algorithm from the rpart package.

Data Prep

Split the data (10127 observations), into training and validation datasets (70%/30% , 7137/2990)

The Tree

Variable Importance

Interesting how months on the is perceived by many as a predictor for Attrition. However, the data shows that it is not a good predictor.

Model Accuracy

Using the validation data, the model accuracy can be observed

## 
##  
##    Cell Contents
## |-------------------------|
## |                       N |
## | Chi-square contribution |
## |           N / Row Total |
## |           N / Col Total |
## |         N / Table Total |
## |-------------------------|
## 
##  
## Total Observations in Table:  3016 
## 
##  
##                                          | validation_tree$Attrition_Flag 
## validation_tree$Attrition_Flag_predicted | Attrited Customer | Existing Customer |         Row Total | 
## -----------------------------------------|-------------------|-------------------|-------------------|
##                        Attrited Customer |               380 |               103 |               483 | 
##                                          |          1229.819 |           227.601 |                   | 
##                                          |             0.787 |             0.213 |             0.160 | 
##                                          |             0.807 |             0.040 |                   | 
##                                          |             0.126 |             0.034 |                   | 
## -----------------------------------------|-------------------|-------------------|-------------------|
##                        Existing Customer |                91 |              2442 |              2533 | 
##                                          |           234.506 |            43.400 |                   | 
##                                          |             0.036 |             0.964 |             0.840 | 
##                                          |             0.193 |             0.960 |                   | 
##                                          |             0.030 |             0.810 |                   | 
## -----------------------------------------|-------------------|-------------------|-------------------|
##                             Column Total |               471 |              2545 |              3016 | 
##                                          |             0.156 |             0.844 |                   | 
## -----------------------------------------|-------------------|-------------------|-------------------|
## 
##  
## Statistics for All Table Factors
## 
## 
## Pearson's Chi-squared test 
## ------------------------------------------------------------
## Chi^2 =  1735.325     d.f. =  1     p =  0 
## 
## Pearson's Chi-squared test with Yates' continuity correction 
## ------------------------------------------------------------
## Chi^2 =  1729.632     d.f. =  1     p =  0 
## 
##

the financial impact of the model, given the following assumptions: the customer retention program consists of forgiving the anual fee of $100 (on average) the value of a customer is $2,300 per year (on average) customer retention programs have a 30% success rate

The financial impact is $267,840 in savings from the retention program