Sandhills Bank would like to increase the number of customers who use paperless banking as part of the rollout of its e-banking platform. Management has proposed offering an increased interest rate on a savings account if customers enroll for comprehensive paperless banking. To forecast the success of this proposal, management would like to estimate how many of the 200 current customers who do not use paperless banking would accept the offer. The IT company that handles Sandhills Bank’s e-banking has provided anonymized data for 1,000 customers from one of its other client banks, Plains Bank, that made a similar promotion to increase paperless banking participation. For these 1,000 customers in the file plains, each observation consists of the average monthly checking account balance, the age of the customer, and whether the customer enrolled for paperless banking. Apply logistic regression with lasso regularization to classify observations in the file plains as enrolling in paperless banking or not by using Enroll as the target (or response) variable. Use 100% of the data for training and validation (do not use any data as a test set).

a. Determine the lasso regularization penalty that maximizes AUC in a validation procedure.

b. For the level of lasso regularization identified in part (a), what are the values of the intercept and variable coefficients in this final model? Interpret the coefficients.
Does the lasso regularization eliminate any variables?

c. The file sandhills contains data corresponding to Sandhills Bank’s 200 current customers. As Sandhills has not yet launched its promotion to any of these 200 customers, these observations only have data for the average monthly checking account balance and age of the customer, but no column for whether the customer enrolled for paperless banking. Sandhills would like to estimate the likelihood of these customers enrolling for paperless banking. Apply the final model selected in part

(e) to the 200 observations in the file sandhills. Using a cutoff value of 0.5, how many of Sandhills Bank’s 200 customers does the final model predict will enroll for paperless banking?