Sunnyville Bank wants to identify customers who may be interested in its new mobile banking app. The worksheet called Mobile_Banking_Data contains 500 customer records collected from a previous marketing campaign for the bank’s mobile banking app. Each observation in the data set contains the customer’s age (Age), sex (Male/Female), education level (Edu, ranging from one to three), income (Income in $1,000s), whether the customer has a certificate of deposit account (CD), and whether the customer downloaded the mobile banking app (App equals 1 if downloaded, 0 otherwise). A portion of the data set is shown in the accompanying table. Create a classification tree model for predicting whether a customer will download the mobile banking app. Assign one as the success class as we are more interested in identifying customers who download the app. Select the best-pruned tree for scoring and display the fullgrown, best-pruned, and minimum error trees.

a. How many leaf nodes are in the best-pruned tree and minimum error tree? What are the predictor variable and split value for the root node of the best-pruned tree? 

b. What are the accuracy rate, sensitivity, specificity, and precision of the best-pruned tree on the test data? 

c. Generate the decile-wise lift chart. What is the lift value of the leftmost bar of the decile-wise lift chart? What does it imply? 

d. Generate the ROC curve. What is the area under the ROC curve (or AUC value)? 

e. Score the 20 customers in the Mobile_Banking_Score worksheet using the best-pruned tree. How many of the 20 new customers will likely download the mobile banking app based on your classification model? What is the probability of the first new customer downloading the app?

Transcribed Image Text:

Age 32 40 Female Sex 26 Male Female Edu 1 1 ⠀ 3 Income 0 1 1 215 CD App Yes 0 No 0 A Yes B 1