Background: As a bank, you tested sending credit card offers to you existing customers. You tested sending the offers via mail as a postcard or a letter. You also tested different kinds of rewards (Points, Cash Back, and Air Miles). In addition, you captured a variety of customer characteristics including income (High, Med, Low), Credit Rating (High, Med, Low), and a variety of relationship variables including number of bank accounts and balances. The offers were sent to a random sample of 18,000 of your customers and you captured whether or not each customer responded to the offer (opened the credit card account). All of this information is captured in the file “creditcardmarketing-bbm.jmp” (field definitions are listed below). Please use that file to complete the following activities and answer the following questions (Notes: you can answer in bullets, short sentences and visualizations; but make sure your answers are complete and Understandable.
1. Create a distribution of Offer Accepted. Yes means the offer was accepted. What percentage of offers were accepted (5 points)?
2. Use the Make Validation Colum utility to create a training, validation, and test sets. What percentage of offers were accepted in each of the three sets of data (training, validation, and tests)? (5 points)
3. Create at least three different models, using different modeling techniques (e.g., decision tree, boosting, bagging, logistic) predicting who is likely or not likely to accept the offer. For each model, create what you believe is the best version of that model.
4. Use the model comparison platform to compare the model’s performance. Which model is the best model? Please explain why (30 points).
5. Based on the models you created, what are major insights? What variables are important in predicting which customers are likely to accept the offer? What characteristics of the offer impact the likelihood customers accept the offer? What are the general business insights gleaned from these model builds? (30 points)
6. Please describe how you might use this model to generate business value in credit card marketing campaigns (30 points).
Customer Number: A sequential number assigned to the customers (this column is hidden and excluded – this unique identifier will not be used directly).
Offer Accepted: Did the customer accept (Yes) or reject (No) the offer.
Reward: The type of reward program offered for the card.
Mailer Type: Letter or postcard.
Income Level: Low, Medium, or High.
# Bank Accounts Open: How many non-credit-card accounts are held by the customer.
Overdraft Protection: Does the customer have overdraft protection on their checking account(s) (Yes or No).
Credit Rating: Low, Medium, or High.
# Credit Cards Held: The number of credit cards held at the bank.
# Homes Owned: The number of homes owned by the customer.
Household Size: Number of individuals in the family.
Own Your Home: Does the customer own their home? (Yes or No).
Average Balance: Average account balance (across all accounts over time).
Q1, Q2, Q3 and Q4 Balance: Average balance for each quarter in the last year.