31. FILE Credit Card. A home improvement retail store is offering its customers store-branded credit cards that come with a deep discount when used to purchase in-store home improvement products. To maintain the profitability of this marketing campaign, the store manager would like to make these offers only to the customers who are likely to carry a high monthly balance on the credit card. A data set obtained from a nationwide association of home improvement stores contains records of 500 consumers who carry similar credit cards offered by other home improvement stores. Relevant variables include Sex (Female or Male), Education (1 if did not finish college, 2 if undergraduate degree, 3 if graduate degree), Children (1 if have children, O otherwise), Age (1 if below 20 years old, 2 if 20-29 years, 3 if 3039 years, 4 if 40-49 years, 5 if 50-59 years, 6 if 60 years and older). Balance is the target variable where one indicates the customer maintains a high monthly balance, and O otherwise. A portion of the CreditCard_Data worksheet is shown in the accompanying table. Sex Education Children Age Balance Female 2 Yes 3 1 Male 1 No 4 0 : : : ... : Female 2 Yes 3 0 A) Partition the data to develop a nave Bayes classification model. Report the accuracy, sensitivity, specificity, and precision rates for the validation dataset. Use 70-30 Training and Validation split with 12345 as the random seed. Accuracy: Sensitivity: Specificity: Precision: B) Generate the ROC curve for the validation dataset. What is the area under the ROC curve (or the AUC value)? AUC: C) Score the new customer records in the CreditCard_Score worksheet. What is the scoring result of the first customer record? D) If we change the cutoff value to 0.3, what is the new scoring result of the first customer record in the Credit Card_Score worksheet? No Sex Male Female Male Female Female Male Female Male Female Education Children Age 1 Yes 2 2 No 3 1 Yes 5 3 5 1 No 1 2 No 4 1 3 3 3 Yes 4 2 No 1 Yes 31. FILE Credit Card. A home improvement retail store is offering its customers store-branded credit cards that come with a deep discount when used to purchase in-store home improvement products. To maintain the profitability of this marketing campaign, the store manager would like to make these offers only to the customers who are likely to carry a high monthly balance on the credit card. A data set obtained from a nationwide association of home improvement stores contains records of 500 consumers who carry similar credit cards offered by other home improvement stores. Relevant variables include Sex (Female or Male), Education (1 if did not finish college, 2 if undergraduate degree, 3 if graduate degree), Children (1 if have children, O otherwise), Age (1 if below 20 years old, 2 if 20-29 years, 3 if 3039 years, 4 if 40-49 years, 5 if 50-59 years, 6 if 60 years and older). Balance is the target variable where one indicates the customer maintains a high monthly balance, and O otherwise. A portion of the CreditCard_Data worksheet is shown in the accompanying table. Sex Education Children Age Balance Female 2 Yes 3 1 Male 1 No 4 0 : : : ... : Female 2 Yes 3 0 A) Partition the data to develop a nave Bayes classification model. Report the accuracy, sensitivity, specificity, and precision rates for the validation dataset. Use 70-30 Training and Validation split with 12345 as the random seed. Accuracy: Sensitivity: Specificity: Precision: B) Generate the ROC curve for the validation dataset. What is the area under the ROC curve (or the AUC value)? AUC: C) Score the new customer records in the CreditCard_Score worksheet. What is the scoring result of the first customer record? D) If we change the cutoff value to 0.3, what is the new scoring result of the first customer record in the Credit Card_Score worksheet? No Sex Male Female Male Female Female Male Female Male Female Education Children Age 1 Yes 2 2 No 3 1 Yes 5 3 5 1 No 1 2 No 4 1 3 3 3 Yes 4 2 No 1 Yes
