Assignment 8
Dylan Isaac & Hunter Eskenazi
2024-04-11
Objective
Predict customer attrition using the classification algorithm from
the rpart package.
Data Prep
70/30 data split data (10127 observations) into training (70) and validation (30) datasets
The training data has 7137 observations
The validation data has 2990 observations
The Tree
Two Interpretations from the Tree
Most likely attrited customers:
- total transaction count (last 12 months) < 55
- total revolving balance < 614
- total ∆ in transaction count (Q4 over Q1) > 0.65
- total relationship count (no. of products held by customer) < 3
Least likely attrited customers:
- total transaction count (last 12 months) > 55
- total transaction amount (last 12 months) < 5423
Variable Importance
Model Accuracy
Using the validation data, it is observed that the model is able to:
Predict attrited customers correctly 75.5% of the time.
Misclassify existing customers as attrited 3.6% of the time.
##
##
## Cell Contents
## |-------------------------|
## | N |
## | Chi-square contribution |
## | N / Row Total |
## | N / Col Total |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 2990
##
##
## | validation_tree$attrition_flag_predicted
## validation_tree$Attrition_Flag | Attrited Customer | Existing Customer | Row Total |
## -------------------------------|-------------------|-------------------|-------------------|
## Attrited Customer | 364 | 118 | 482 |
## | 1155.572 | 206.873 | |
## | 0.755 | 0.245 | 0.161 |
## | 0.802 | 0.047 | |
## | 0.122 | 0.039 | |
## -------------------------------|-------------------|-------------------|-------------------|
## Existing Customer | 90 | 2418 | 2508 |
## | 222.084 | 39.758 | |
## | 0.036 | 0.964 | 0.839 |
## | 0.198 | 0.953 | |
## | 0.030 | 0.809 | |
## -------------------------------|-------------------|-------------------|-------------------|
## Column Total | 454 | 2536 | 2990 |
## | 0.152 | 0.848 | |
## -------------------------------|-------------------|-------------------|-------------------|
##
##
## Statistics for All Table Factors
##
##
## Pearson's Chi-squared test
## ------------------------------------------------------------
## Chi^2 = 1624.287 d.f. = 1 p = 0
##
## Pearson's Chi-squared test with Yates' continuity correction
## ------------------------------------------------------------
## Chi^2 = 1618.706 d.f. = 1 p = 0
##
##