Description
The project will be broken down into 3 phases:
- Phase 1 – MARS and GAMs
- Phase 2 – Tree-Based Models
- Phase 3 – Model InterpretationObjective – Phase 2
The scope of services in this phase includes the following:
- For this phase use only the insurance_t data set.
- Previous analysis has identified potential predictor variables related to the purchase of the
insurance product so no initial variable selection before model building is necessary.
- The data has missing values that need to be imputed.
o Typically, the Bank has used median and mode imputation for continuous and
categorical variables but are open to other techniques if they are justified in the report.
- The Bank is interested in the value of random forest models.
o Build a random forest model.
- (HINT: You CANNOT just copy and paste the code from class. In class we built a
model to predict a continuous variable. Make sure your target variable is a
factor for the random forest.)
o Tune the model parameters and recommend a final random forest model.
- You are welcome to consider variable selection as well for building your final
model. Describe your process for arriving at your final model.
o Report the variable importance for each of the variables in the model.
- Pick one metric to rank things by – no need to report multiple metrics for each
variable.
o Report the area under the ROC curve as well as a plot of the ROC curve.
- (HINT: Use the same approaches you used back in the logistic regression class.)
- The Bank is also interested in the value of an XGBoost model.
o Build an XGBoost model.
- (HINT: You CANNOT just copy and paste the code from class. In class we built a
model to predict a continuous variable. You will need to look up the
documentation for the ‘objective = “binary:logistic” ‘ option.)
- Use the area under the ROC curve (AUC) as your evaluation metric instead of
the default in XGBoost.
o Tune the model parameters and recommend a final XGBoost model.
- You are welcome to consider variable selection as well for building your final
model. Describe your process for arriving at your final model.
o Report the variable importance for each of the variables in the model.
o Report the area under the ROC curve as well as a plot of the ROC curve.
- (HINT: Use the same approaches you used back in the logistic regression class.)Data Provided
The following two sets of data are provided for the proposal:
- The training data set insurance_t contains 8,495 observations and selected variables.
o All of these customers have been offered the product in the data set under the variable
INS, which takes a value of 1 if they bought and 0 if they did not buy.
o There are selected variables describing the customer’s attributes before they were
offered the new insurance product.
- The validation data set insurance_v contains 2,124 observations and selected variables.
- The table below describes the Roles and Description of the variables found in both data sets.
o Except for Branch of Bank, consider anything with more than 10 distinct values as
continuous.Name
Model Role
Description
ACCTAGE
Input
Age of oldest account
DDA
Input
Indicator for checking account
DDABAL
Input
Checking account balance
DEP
Input
Checking deposits
DEPAMT
Input
Total amount deposited
CHECKS
Input
Number of checks written
DIRDEP
Input
Indicator for direct deposit
NSF
Input
Number of insufficient fund issues
NSFAMT
Input
Amount of NSF
PHONE
Input
Number of telephone banking interactions
TELLER
Input
Number of teller visit interactions
SAV
Input
Indicator for savings account
SAVBAL
Input
Savings account balance
ATM
Input
Indicator for ATM interaction
ATMAMT
Input
Total ATM withdrawal amount
POS
Input
Number of point of sale interactions
POSAMT
Input
Total amount for point of sale interactions
CD
Input
Indicator for certificate of deposit account
CDBAL
Input
CD balance
IRA
Input
Indicator for retirement account
IRABAL
Input
IRA balance
INV
Input
Indicator for investment account
INVBAL
Input
INV balance
MM
Input
Indicator for money market account
MMBAL
Input
MM balance
MMCRED
Input
Number of money market credits
CC
Input
Indicator for credit card
CCBAL
Input
CC balance
CCPURC
Input
Number of credit card purchases
SDB
Input
Indicator for safety deposit box
INCOME
Input
Income
LORES
Input
Length of residence in years
HMVAL
Input
Value of home
AGE
Input
Age
CRSCORE
Input
Credit score
INAREA
Input
Indicator for local address
INS
Target
Indicator for purchase of insurance product
BRANCH
Input
Branch of bank
